Just preordered -- glasses request: there's no way to say it nicely, I have a big nose. With a high bridge. Many glasses are really tough to get properly placed; may I request you not give up on the pads w/metal adjusters that you have in the product photos? Don't let a designer take them away from you, us folks not one standard deviation from 'normal' noses will thank you.
Second, how tough is this signal processing? Will it be done on-glasses, or through an app? Third, what's the equivalent of a wake word for these? I'm reminded of the Apple Vision Pro radar to see if your fingers are clicking. I could imagine a lot of modalities where I want to just start talking and have things happen, and a lot where I don't want the glasses to pick it up. Fourth, I think a cool voice change demo would be rad -- not sure what latency is like, but if you could get it end to end under like 250ms you could probably have someone exaggerate the mouth movements and pipe out audio of them talking like someone else. Which would be another really cool demo.
Super cool. You're going to be working 80 hour weeks for the next year, I'm excited to see what you put out!
Yep, we have been quite set on nose pads to keep them comfortable. I will keep you updated with the designs!
The decoding is done via a companion app on your laptop or phone in the cloud, but end to end latency is still quite fast, under 500ms usually.
To begin with we don't plan to have a wake word, but rather a trigger key on your connected device that you're entering text into (pressing Alt for example), similar to Wispr Flow. We're doing some R&D into the silent speech equivalent of voice activity detection, so we have a low power basic RF detection always-on, not enough to decode speech from but enough to detect rough movement, and when it detects speech-like activity beginning to start we can trigger full sensing within tens of ms. This would likely ship as a software update a few months after shipping, though.
The voice change demo is something I've thought about actually, but we never got around to doing. Might film it soon :)
Super cool. For a cool voice change demo we'll allow a gb200 over low latency wifi :) elevenlabs has deals with a number of professional actors and voice actors for licensed uses, seems like you could probably find an ethical and cool co-brand opportunity in there.
Wait. You are taking the RF response, sending it up to the cloud to interpret, and then sending the result back? Hard pass from me, sorry. Cool tech, but I don’t want my internal thoughts anywhere near the cloud. Also, this would mean I couldn’t use something like this on the subway when the phone signal goes out intermittently, right?
One thing you might consider is actually telling people what it is on the homepage. Took me a fair bit of work to understand that this is effectively a pair of smart glasses.
Maybe I could have figured that out from the video but for folks who can’t watch the video it’s quite hard to discover what you’re building.
I think this is incredibly cool and straight out of a sci-fi novel! I think this is phenomenal for accessibility and for hands-free computing in general. I also agree with other comments that the website should have more detail on how it works, such as what you included in the post body. Amazing work guys!
I second that. I've been talking and talking to my phone and AI even more and more since it keeps getting better and is generally pretty accurate these days. And there are times when I end up typing because of environmental reasons.
This is just really groundbreaking and I know the research has been out there for a little while but to actually implement is a whole nother ball game.
I think the use cases for this will expand as the product ships and gets out there!
Agree, incredibly cool, and I could definitely see myself using one, but it does give off slightly dystopian vibes, making me think of the speakwrite in 1984:
"In the long, windowless hall, with its double row of cubicles and its endless rustle of papers and hum of voices murmuring into speakwrites, there were quite a dozen people whom Winston did not even know by name"
Based on my understanding of the technology, this also means you can effectively dictate in loud environments. Correct?
I find that I need this most often when I'm doing yard work, running equipment, or cleaning out the garage. Audio based microphones pick up so much noise.
This is also neat thing to have with people struggling with typing (RSI, injuries, disabilities) but want to do more than just dictation, eg Talon Voice. A common problem with voice commands and dictation alone is that people find they're hurting their vocal chords pretty quickly. Neat.
If the tech is mostly in the glasses temples, I would prefer to have something that attaches to my existing glasses. I have prescription glasses and a big head, tried the Even G2 smart glasses and the available frames set just too small for me
+100 on this! My choice of glasses (and prescription) has nothing to do with my choice of how to talk to my computer. Don't risk failure just because you make them depend on each other.
Might not even need buds. I have watched movies on XReal glasses with the sound fairly loud to me next to other people and they didn't notice a thing (I asked them to be sure).
The glasses will have open ear speakers similar to meta glasses! We plan to make our own agent harness and connect it native with the glasses. I have meta glasses but rarely use the AI since it's weird to talk out loud to ask it things when I'm out. This is how we want to solve it
> "you don't actually have to move your lips or even open your mouth for this to work ... It's a bit weird to do"
In the video Dave just finished the training mode and is silently moving his lips, which seems pretty natural to me. I just spent a minute trying to do 'internal speech' (as many elements of speech as possible with lips closed). It does feel weird and seems like internal speech is probably providing a fair bit less signal for the system to sense (in both signal freq and amplitude). I realized I can't guess at how much articulation is 'enough' without feedback.
Based on that I'm guessing adapting to internal speech might follow a bit different path than silent speech, which seems more like 'just do what you already do silently'. Extrapolating, I expect training internal speech might involve more real-time feedback to help the user find the right degree and kind of articulation.
I realize you're still in the prototype phase but I assume an increasing number of people are getting multiple longer sessions. Do new users advance from silent to internal speech quickly and stay there? I'd be surprised as, intuitively, 'Silent -> Internal' seems like a bigger step than 'Normal -> Silent'.
Separately, if I was using it daily, I can imagine wanting to evolve a kind of micro-expression shorthand for 'Yes', 'No', 'Pause' and 'Stop', since two humans naturally evolve similar non-verbal queues over time. Vocalizing words is flexible and expressive but not efficient. It would seem odd if an intelligent, adaptive 'invisible friend' living on my face for years didn't adapt to me and me to it. Are you guys thinking in those directions for the future?
Cue the resurgence of lip reading-based espionage. Imagining having to scan the room for people watching subvocalizers. Will subvocalizers start holding up a clipboard over their face a la NFL coaches?
That's already been a problem ever since people figured out you can recover voice from watching the subpixel vibration of objects within a room. (Video: https://www.youtube.com/watch?v=eUzB0L0mSCI)
Most people type at 40-50 WPM. Developers can often type at 70-100 WPM. Meanwhile, most people can talk at 120-200 WPM. Beyond just speed, we've found with many people that talking things out tends to flow more naturally, since it's often a lower friction action so people don't "sanitize" the text in their head before outputting it. Leads to better prompts quite often :)
> talking things out tends to flow more naturally,
I've found the opposite. Typing feels much more "deliberate", and of course you can hit backspace but you can't un-speak a word. With prompting, I've found that, in general, speaking leads to lower-quality results than typing.
I was surprised to find after using dictation heavily all year that I actually talk a load of rubbish when I'm speaking, using all kinds of cliches and fillers and saying way more than was needed.
Yes, I feel very similar. Maybe it's just that my verbal intelligence is lower than average but it feels that the signal to noise ratio is much lower when I speak off the cuff vs when I type.
My spouse and I have a rule that if we think a discussion is going to be emotionally charged, we have it over text in different rooms.
It sounds autistic, but writing and reading allow you to be much more precise, careful, and deliberate with your words and helps reduce impulsive outbursts.
This has worked really well for us, as crazy as it sounds.
Not everyone. I, at least, definitely overthink what I type, and while I end up with nice-ish sentences in my prompts it takes a lot longer than a train of thought that the AI parses correctly most of the time anyway.
Also, speech is probably bottlenecked by speed of thought, not making the sounds. I recall some study showing that data rate is pretty consistent between languages, despite wpm varying significantly due to language verbosity. You can try it yourself: try to quickly repeat “one two three four five” then try to read a paragraph out loud as quickly as you can, I bet you can feel the first strain your muscles and the second your brain, and I bet the first blows your typing wpm out of the water.
But what you're calling 'talking things out' I consider to be forming thoughts. I want to do that myself upstream of the LLM. I don't want to pay per token for my half-baked stream of consciousness.
I'm dyslexic and while I can type fairly quickly it's always a struggle to get the spelling and typing mistakes fixed. Talking is a much more natural way to express myself. The frustration of not being able to spell the word that I want doesn't exist. Mis-transcription errors are of course an issue, but those are getting fewer and fewer.
When I try talking for prompting my coding agents, I'm always severely disappointed with the specificity of the prompt. It's just much easier for me to "talk about" coding specifics with a keyboard than it is for me to speak about them, for some reason.
I suspect this has to do with the nature of the work you're doing; I dunno, just count me firmly in the camp of people who only rarely feel like I can express a thought sufficiently for coding agents with their voice.
I guess it depends on how close to the code you want to work. I find that I lately talk only about the features and UX and can leave the coding details completely to the agent. That might not work in every project, but I suspect it might work more often than people think because it's hard to adapt to the quickly increasing capabilities of LLMs.
I think a good habit is: Try to make the agent fail at least once a week with a too ambitious request. This got surprisingly hard lately :)
I'm the same. I also can think ahead / along much better while typing. When I'm talking I'm just talking, not thinking as much.
But I guess thinking is going out of style anyway.
That said, I know a lot of people prefer talking to their computer, especially when their computer is a phone. So there is definitely a place for stuff like this.
You need to train yourself to speak written speech. When you do that, the thought processes behind typing your words activate, and your language use changes.
As a person who often talks far too fast and incoherently, but types generally fast and legibly, I had never recognised or even considered this, but it seems helpful. Thanks.
One approach is reading your and other people's written speech out loud. Pay attention to where it feels awkward; for me, that was the direction I needed to practice. A trick that I use currently to reinforce speaking written speech is using Grammarly to make corrections, which I try to internalize.
Another trick is don't correct words and letters. Say the sentence you really meant to say. It is not uncommon for me to say a thought or a concept two, three, four times in a row as I'm wrestling with what the language should be on the written page.
This has been an interesting thing for me to watch as it's such a case of people having widely different experiences. I'm sure people that didn't grow up on a keyboard like me can probably talk quicker than they type, but even aside from me being a fairly good typist my speech is held up by being a bit more halting, a bit more of backtracking on word choice, sometimes not quite the same 'voice' of writing as I'm aiming for, all of which obliterates any speed advantage it'd have for me.
But happy to see people get more options.
This reminds me of Eternity's End by Jeffrey Carver and the implants they had. Released in 2000 but the more time goes on the more the neural implant technology is coming about. To be fair I think Enders Game had similar tech to detect subvocal speech like this product.
> This has been an interesting thing for me to watch as it's such a case of people having widely different experiences.
Same. I'm often told I talk too fast, but I feel I communicate slowly because a lot of my fast speech involves halting and backtracking and such.
I can easily type 100WPM+, but I trivially blast out a few paragraphs of perfectly adequate text in a few seconds and then spend a few minutes re-editing it.
Yes, I'd estimate the vast majority of people speak faster they can type. Not sure about the thinking part because I usually have 20 threads going parallel in my head and can't imagine what normal thinking would be like.
For the ones thinking this is great, have you actually tried to talk without making sounds?
I don't think it is an intuitive action at all and I became self-conscious about not making a sound rather than talking like I normally would.
I suppose it would require some "getting used to."
Regardless, I think it is a cool idea and a real problem. Sometimes I don't want to type nor talk out loud so I find myself whispering at my phone like I'm telling it a dirty secret.
--
As I'm writing this, I think this kind of product might not hit the market for consumers, but I'm seeing this used by Flock like companies to spy on people's speech, so kudos on making machine lip reading a thing!
There's already open-source stuff [1][2] out there that can lipread video to transcribe text, but the word error rate is pretty high (and it may not be physically possible to get this down without doing something like subvocal and having other sensors near your face).
Have you never talked / mouthed without making sounds? Never even as a kid when something made you mad and you paced around the room think-saying shower thoughts to get back at that person? Even as an adult I probably mouth a sentence or two e.g. "What the fuck is this" when looking at AI output 3-5 times a week
It does feel a little weird to do it voluntarily when not emotional, but that'll be solved as soon as Claude fucks something up :)
First, I absolutely hate having to scroll and scroll and scroll and scroll to try and figure out what's going on.
Second, I read this:
"The current prototypes already decode open-ended silent speech in real time, and accuracy continues to improve as we collect more data and train larger models. Like any input method, it can occasionally get something wrong, so the product is designed to use context and easy corrections rather than pretending errors never happen."
And I have to ask, does this mean everything I vocalize is being sent to an unknown server to be analyzed, potentially read by a person, and then used to train your model further? Because that's clearly not going to fly for either me or my employer. You need to be crystal clear what information people are potentially sharing with you before they purchase your devices.
I remember seeing AlterEgo a few years ago and thinking it was so cool (obviously was missing voice agents to make it really cook)
Was just thinking this could be applicable for people with some disabilities tied to an actual voice agent and speaker. Or even in foreign countries where you talk and respond in the foreign language instead of waiting for an additional translation layer.
I am so glad to see an unpolished early look and an honest evaluation of about five percent error rate in the YouTube video. The really cool stuff will be the applications on top of `subvocal` though at least in my opinion.
So this could take "noise canceling" to a whole new level if you could somehow "speak" across a loud bar or across the world, for that matter. Being integrated into something like Signal or similar end to end encrypted platform would be interesting as well.
Yep, I agree. Noise cancellation is a feature we want to release at some point in the future. Using the RF to denoise a very noisy audio signal which has you speaking in it. And we'll release an SDK as well a few months after shipping to build stuff on top of it!
I had to look it up, I forgot he communicated with her through sub-vocalizations. I remember the jewel earpiece, but in my head he just communicated through thoughts or something.
Good reference! That series of books Is one of my all time favorites.
I mean we're getting pretty close here -- you could have these + your AirPods in transparency mode up and you're not far off. Also Claude won't currently ice you out for going dark, unlike Jane.
With so many people singing the praises of voice to text, I keep thinking about how most sci-fi futures feature subvocalization as a prerec for that kind of adoption. Always love to see sci-fi come to life!
For about 15 minutes until they figure out what's going on, take those folks out back and "convince" them to spill the beans on how it work, then come up with a way to detect and prevent it moving forward.
Very cool! I was curious to hear the details of how it worked but couldn’t find them on your landing page. I’m glad to see them here and you might want to include them more prominently on the page itself. I didn’t even realize it was a pair of glasses til I read the above.
E.g. your FAQ says it doesn’t use cameras but does not say what it does use. And when I got to the footer and clicked the “how it works” link, it seemingly took me back to the top of the page I had just read.
Can someone comment on the AirPods tweet making the rounds (i.e. the subvocal killer)? I am excited by Subvocal, but am wondering how much bespoke hardware is actually required?
Yup we worked with IMUs as well when we started this. They measure aggregated face motion, so cannot distinguish between fine phonetic classes, only broad words. The open source demo got to a 5 word classifier, I believe. We tried a lot to make IMUs work too, in various form factors, but the signal doesn't contain enough information for open ended decoding beyond classifying between a few words. We would have loved to be able to just push software!
> There was this really interesting one where it reads your lips
This is what I thought the original post was about. The glasses you have to wear is where that lost me.
If we could get lip-reading via your computer/phone camera down perfectly, that's the real win. Making people wear your goofy frames is where you lose a massive portion of people. Nobody wants to look like Zuckerberg lol
Lip reading is one of the other modalities we tried as well beyond IMU, EMG and RF! We worked a lot on fine tuning Auto-AVSR, one of the most commonly used open source lipreading models. It's very enticing to work on, since it gets to about 17% word error rate, which looks good enough that you would think working on it further would get it down to product quality, but we found there's an information-theoretic limit on the modality. Speech has 40 phonemes, but only about 12 to 15 visemes (externally visually separable phonetic states). For example P and B look very similar from a camera. This causes the scaling laws on lipreading to flatten out at an error that's too high to be product ready but just low enough to make for a good demo. Our original plan was actually to ship a lipreading software to see if people would want this behavior, but we realized you couldn't make lipreading work!
Not well enough! You can get to 15-20%ish WER but going beyond that doesn't seem feasible with the info available from a camera, even with a great language model
I have this problem and I was wondering how it would be solved. For now I can cope because I mostly work from home but I’ll keep track of you guys. Best of luck!
Theres a LOT of people working on this.. Cornell have been putting students on this task for about 5 years.. Lots of fun different ways of doing it. Interesting you went the radar from glasses route.. I wish you well. Yet to see a product apart from the odd lip reading ML project that makes it into a product..
I'm waiting for throat tape a la that one paper where whatever you say in your head translates to micro movements in your throat/jaw or something like that.
Super excited to see more products in this area. I talk to my computer the majority of the time now, and I can do that because I work from home. If I were on public transportation or in an office, it would be much more difficult. It's been interesting to watch the Overton window, if you will, shift for people talking _to_ their phones. Now, the majority of my family will use voice to text on their phone whereas I remember just a few years ago, if not even just a year ago, it was made fun of.
I think these have a place but I can't say the same for most other new AI communication devices. Creeper glasses, pins, watches, desktop units etc. I want to be able to speak and hear from my agents at all times but why would I want a new device when I already wear earbuds? New products are being designed to pick up low murmuring/whispering, like the Subtle earbuds, but I assume most earbuds will be designed this way in future.
I'm curious about whether this could be done with the hardware mounted on top of the laptop screen or on a stand on the desk, rather than the glasses form factor. Have you explored this?
Yes, we have! The same kind of RF doesn't work in that form, since it is attenuated strongly over that big of a distance. But the other interesting alternative we tried it mmWave radar, RF at about 60 GHz, the same band as 5G. This is much more similar to conventional radar, in that it would bounce off the face rather than passing through it like our current system. We found a few problems with this:
1. It faced the same issue as cameras. mmWave radar has a very low penetration in tissue, so it basically just bounced off the mouth. This only let us see visemes, which aren't enough to get to a low error rate as complete phonetic decoding can.
2. While mmWave radar can detect skin movement as small as a few microns via Doppler shift (given it's small wavelength), its spatial resolution with most systems is quite low. For example, it can tell that something moved 2 microns but within a 5cm x 5cm block. This coarse information makes it very hard to decode
That's why we weren't able to make something that can mount to your laptop. We're trying to make a necklace form factor at some point in the future though, but can't give a date on this!
I would be fairly interested if this works without opening my mouth. Like, if you can nail _micro_ tongue movements, it would feel pretty close to thought.
It actually can! Since the RF can see inside your mouth the system doesn't inherently need lip movements and can be fine tuned on what we call "internal speech". Note that this isn't the automatic tongue movements that occur when "thinking" words to yourself, but it's rather like mouthing with your lips closed. We don't often lead with this since it's weird for many people to do, but with a bit of practice, we have been able to get it down pretty well.
Vowels definitely require tongue movement! Leave your mouth closed and whisper "a-e-i-o-u" and you can feel your tongue moving.
Vowels change the shape of your mouth's cavity to change which frequencies to emphasize ("formants") and we hear the differences in vowels by analyzing those formant patterns.
There's subtle changes in internal speech muscles as well often for those kinds of movements, and where it does seem ambiguous language context is usually enough to distinguish
This is very cool, but oddly, the site is TOO focused on the user problem being solved to the extent that it feels like snake oil. The issue is that this is contrary to people's experience of what is possible, so without discussing WHY you can do this, it looks like a scam or vaporware.
What I would really like is a washable "cyber suit". Mock or turtle neck (for the voice / STT capture / control), EEG sensors, breathing rate, blood pressure, gestures via arm motion sensors,). Removable rechargeable battery module to wash the torso / shirt slap it on a clean one. For EEG it would have to be pretty compressed though, so not sure it would be comfortable enough to wear to sleep? maybe only an internal harness needs to be that compressed. not sure. I'm tired of wearing a Fitbit, or glasses, or these different things people have to look at, keep up with, break easy etc.
Pretty cool! My only wish is that all this kind of work didn't gravitate toward glasses or assume glasses are the default thing-on-your-face now. 3/4 of humans don't wear them, and even some of us blind bats hate them enough that we endure the hassle of contact lenses!
Should really just be like a leap motion device on the desk, glasses are so gimmicky and aren't gonna fly for people with prescriptions (a large set of people in-front of computers all day)
If no one wants to dictate to their phones or computers in public, surely they don't want to do this (looking like they are talking without making any noise) in public?
Neat! I don't like talking to my computer (audibly or not), but that's a cool demo.
I wonder if we could eventually end up with a "throat muscle" version where people learn to talk a new way without having to move the visible mouth muscles too.
This is amazing, brilliant idea and nice execution. Are you concerned about Meta or any other established smart glasses players potentially copying such an idea?
Spent 30 seconds scrolling down to try to figure out what this is. Eventually clicked away from the site because it was taking too long to get to the point. I'm sure it's great and I understand it's something to do with glasses and subvocalizations, but consider a one sentence contextualization at the top of the page.
I was just trying to help a vibe coder and immediately noticed that their README.md was over 2,000 lines long. I asked, "Why is your readme so long?" and their response was, "This is just a really complicated application."
The app essentially manages a bunch of TODO items written in markdown.
For some reason AI coding agents seem to think a README should be a Product Requirements Document (PRD).
I think it's because most projects don't have any settled place (or at least, any place that lives inside the project's source-code repo) to record PRD-like information.
But because AI coding agents really do benefit from having PRD-like info (i.e. a hierarchical breakdown of the "intended what" and "intended how" of the system that "should" exist in the repo, kept updated to reflect changing ideas about those intentions), they really want to record that type of info somewhere, so they can then reference it.
AI coding agents don't seem to have any "taste" (or maybe "confidence"?) when it comes to asserting that even if you don't already have a separate PRD-like file in the repo, you should have one, if you want the agent to do its job well, and so it would request you to let it create one (or just automatically do it.) Instead, they just shrug and cram the PRD stuff into whatever structure you do already have. Which, if you're starting fresh with a greenfield project, is usually just a README.
(I hypothesize that if you tell an AI coding agent to use Behavior-Driven Development [BDD] on a greenfield project, it'll probably lean toward maintaining its PRD-like info in the form of BDD test cases. Haven't tried this experiment yet; would be interested to know the outcome!)
That is exactly what happened in this case; the readme was the PRD.
Throughout the document Claude kept claiming that issues were "mitigated but not fixed". They were essentially bandaid fixes for things it couldn't figure out. When I pointed this out to the author he said, "Well Claude thinks it works."
I wonder what happens to software when enough people try to ship projects like this.
Really neat tech! Just curious, how much did you leverage AI during the development? This seems like the type of neat tech that we should expect more and more from wielding our new tools well.
this is super cool. I did some digging about current research on avsr using video and lip point cloud movement a while back. found projects like https://github.com/amanvirparhar/chaplin but this seems more promising!
I've thought about learning sign language in order to communicate with the computer in a not-super-annoying way. Your solution... much more realistic. Cheers.
No, the RF is very low power and can safely be active on your face for long periods. We've done a lot of investigation and verification with safety. While doing R&D the first 2 months we collected hundreds of hours of data on ourselves with various configurations, so we made sure it was safe before :)
Also, the RF transmission only activates when you're actively dictating.
That is fascinating. How do the radio waves get modulated? Do you think it is possible to use this technique for spying technology, with remote transmitters and receivers intersecting a person's facial anatomy to pick up the details of even a whispered or muttered conversation?
Most probably not possible to do this remotely, since this kind of RF needs to be transmitted through the face, and if you transmit them from too far away very few of them will actually take a path that goes through the face and comes back to your receiver.
They get modulated since your mouth is a complex dielectric environment. Tissue, water, and air have different dielectric constants (different permittivity to RF) and the motion of the muscles in this medium leads to interactions with the waves that fill it, changing their phase and amplitude as they propagate.
So it's a pair of glasses that can transcribe when you mouth words silently? I still don't know how it works, they say no cameras and it works with noise so I assume sort sort of reverse bone conducting?
I did research in this space about eight years ago. Our approach was to look at deformations in the ear canal. Rumor has it that Apple AirPods will have sensors in the ear canal. I was hoping to use those sensors with our app, but it looks like Apple is not going to provide access to the raw sensor data. I expected Apple is going to support subvocal speech pretty soon.
From my understanding decoding via ear deformation requires the mouthing to be quite exaggerated. I am also looking forward to Apple launching it soon though, hopefully it gets more people excited and aware about the category at least
The tech sounds cool, but my guess is this product might work for anyone whose text to command ratio is very high. If the formatting and commanding are the main tasks, then this product would be more of a distraction for a fast typist.
Regarding the website, you should lead with product, its details, rather than founders shown in 360 degrees from various vantage points. It is distracting and frankly irritating.
If you're selling a physical product, using AI to model your product seems like a really bad idea. You have no idea if the product actually fits on their faces.
Calling it early - this is a scam. There's no way they're going to deliver that product, in that form factor, by Q1 2027.
Why do you hurt communicating your very cool product with an annoying and counter intuitive scroll experience?
And after some time I could not figure out what this is?
Put this part: " building smart glasses that let you talk to your computer without talking out loud. You can mouth words silently and discreetly and the glasses decode them to text at the speed of speech."
right at the top and maybe show someone actually doing that instead of hiding behind cryptic marketing.
Infuriating website UX, you really must add the scrollbar back. Apple do shiny things like this but they know you can't get rid of the scrollbar and piss people off trying to look at information
Website is shit, "how it works" tells you nothing much useful about how it works, and I assume there is some custom hardware (as described in the post above) but nowhere on the website I could see this actually said, and therefore zero indication of the size of the interface electronics etc etc
Let's go! Love the idea. Like the analog to bone conduction earbuds. Just please don't turn into WisprFlow where they route the voice metadata, unbeknownst to many, to a third party partner who stores and mines it for who-knows-what.
Good luck fellas.
How have the glasses been received? I don't understand why they're required, is it only to have a consistent mount point for the radar sensor, relative to the face? Have you thought about a throat mic?
It looked like there was a throat mic in the first shot... it seems counterintuitive that you'd get better performance out of lidar on face muscles than on a throat mic.
No throat mic, the first image uses EMG (muscle electrical signal) sensors. A throat mic only works if you're still actually whispering (not fully silent) and is also a weird form factor for a consumer device, which is why we didn't go with it!
I'll defer to your expertise on what people find weird, but it seems like you should be able to have a throat-based device that could hide under a shirt collar. I have the Meta Ray Bans and even though I love the functionality, I don't care for the bulky frames. And those are designed by Ray Ban, meaning they're presumably at the upper end of what can be done stylishly.
There is a product by Subtle called Voicebuds that allows for super silent dictation. Looks like the product is not available for purchase yet, but I would prefer to have earbuds over glasses.
Can we use RF for other medical applications? As an anesthesiologist, we do nerve blocks before surgeries or for pain. One rough indicator that it's working is muscle paralysis. Also similar for botox.
Not sure, but definitely sounds interesting! I do know there was one company trying to use mmWave RF to track patient vitals like breathing patterns and heart rate without having anything hooked up to / touching them
Much respect for actual innovation. I hope you get filthy rich.
From your comments it seems to reach this point you tried at least open source lip reading software, IMUs, variant antenna mounting strategies, various frequencies, and then gathered training data. You articulated strongly why the product is desirable and why the failed modes were dead-ends. I hope you can deliver on your pre-orders and are able to scale and/or sell the IP for a strong exit.
There is a long way from a prototype to production. Remember Google Glasses, Oculus, Meta Rayban, Apple Vision Pro?
All of them are visionary and we would think that ppl gonna like them…
Well… ordinary people want boring tech.
This will be similar with whispering to glasses… Visionaries will like it… and return to missionary (boring) s*x (I hope that I don’t get a ban.)
Myself, I would buy these glasses immediately. But I would hate them as well as I would think I am insane (who wants to talk to yourself?).
Edit: Dang replied. I wish all the best to the team behind “whisper glasses”. It is amazing. Connect it with ElevenLabs and you rule the world. (Previous: It wasn’t meant a hate speech.)
This wasn’t meant as a hate. Sorry if it sound so. I really like them, I would buy them. Immediately. Sign me in.
But I think (and see) that people prefer boring tech. Whisper glasses is amazing. But most people will probably find it creepy. (Pareto applied.). I hope I am wrong. These guys are like from sci-fi.
A comment like the GP quickly pattern-matches as snark and dismissal because those are so common on the internet. In other words, if you don't intend your comment that way, you need to do something to disambiguate this. Your follow-up comment does this nicely.
This also leads to a fascinating (to me at least!) phenomenon where the reply to a moderation comment (i.e. your follow-up here) makes explicit the thought which the commenter meant to communicate. What's fascinating is how different this is from what they originally posted. I call this the rebound effect. https://hn.algolia.com/?dateRange=all&page=0&prefix=true&que...
They are claiming 200+ wpm on a prototype. Half that speed would put you in the top tier of typists, and the number of people that get anywhere close to 200 is vanishingly small.
FYI, the subvocal.company site is unscrollable with a mouse wheel in WebKit browsers on Mac (Safari, DDG, Kagi Orion), though the touchpad will work. No issues elsewhere (Mac non-WebKit, Win11, Ubuntu)
Maybe you don't want strangers around you hearing you say "Hey Claude wish my grandma happy birthday" as it's not yet morally okay to delegate such social tasks to the models
Aha what a loser thing to do, I personally have a fleet of 347 agents running 24/7 talking to my parents, siblings, grandparents, friends, asking them how they're doing and wishing them a happy birthday when the time comes. I can finally focus on the important things!
Your example proves their point perfectly. You shouldn't delegate wishing your grandma happy birthday to a fucking AI agent. And you should feel ashamed for doing so. And you should feel the social pressure to hide that fact if you do resort to it.
While this tech doesn't feel quite as dystopian as most recent AI innovations, I do think it is a further step in the direction of human disconnection.
As long as the ROI from social relationships(inheritance, friendship favors, dating/mating potential, etc) can be upheld using less effort, such as language models, its a no-brainer and you lose out to competition if you don't do it.
There is no human connection typing words into a box, that's seems like what it's mostly replacing. Talking to your email client, talking to your AI agent. Lots of us are much faster speaking than typing and especially with AI, it doesn't matter a whole lot in my experience how polished the output is, the benefit from ending up with a lot more text because one can just talk freely is very beneficial.
I can see this being useful on public transport where you don't want to bother people while taking notes verbally. It's not all about avoiding connection.
They're taking pre-orders. Obviously the product doesn't exist yet. The tech is real.
You can like or dislike generated images (if that's what they are—I haven't looked) but this post has nothing to do with scamming anyone, and given the wealth of technical information in the thread, including a video showing the product under development, that seems like a really weird claim to arrive at.
You don't see how this is misleading or fradulent (i.e. definition of a scam) in any way? A realistic image of someone wearing the glasses that don't exist yet, without disclosing it?
You're condemning them for spending all their time making the product work instead of...focusing on their website? Bit strange to call someone a scammer for doing the opposite of what scammers do.
I mean the whole website / linked page is filled with AI generated images. Which is one thing. But very basic, obviously AI generated ones, which makes it worse. At least for me it doesn’t inspire confidence.
p.s. Especially please don't do this when a thread is brand new. Such comments are the easiest to post, and therefore the quickest to appear, but by posting them, you steer the discussion straight away from the curious, thoughtful conversation we want here. Threads are extremely sensitive to initial conditions, so this is important.
When I first saw their promotional video, I thought it was a meme video with the dude mumbling to typing.
Just preordered -- glasses request: there's no way to say it nicely, I have a big nose. With a high bridge. Many glasses are really tough to get properly placed; may I request you not give up on the pads w/metal adjusters that you have in the product photos? Don't let a designer take them away from you, us folks not one standard deviation from 'normal' noses will thank you.
Second, how tough is this signal processing? Will it be done on-glasses, or through an app? Third, what's the equivalent of a wake word for these? I'm reminded of the Apple Vision Pro radar to see if your fingers are clicking. I could imagine a lot of modalities where I want to just start talking and have things happen, and a lot where I don't want the glasses to pick it up. Fourth, I think a cool voice change demo would be rad -- not sure what latency is like, but if you could get it end to end under like 250ms you could probably have someone exaggerate the mouth movements and pipe out audio of them talking like someone else. Which would be another really cool demo.
Super cool. You're going to be working 80 hour weeks for the next year, I'm excited to see what you put out!
Yep, we have been quite set on nose pads to keep them comfortable. I will keep you updated with the designs!
The decoding is done via a companion app on your laptop or phone in the cloud, but end to end latency is still quite fast, under 500ms usually.
To begin with we don't plan to have a wake word, but rather a trigger key on your connected device that you're entering text into (pressing Alt for example), similar to Wispr Flow. We're doing some R&D into the silent speech equivalent of voice activity detection, so we have a low power basic RF detection always-on, not enough to decode speech from but enough to detect rough movement, and when it detects speech-like activity beginning to start we can trigger full sensing within tens of ms. This would likely ship as a software update a few months after shipping, though.
The voice change demo is something I've thought about actually, but we never got around to doing. Might film it soon :)
Super cool. For a cool voice change demo we'll allow a gb200 over low latency wifi :) elevenlabs has deals with a number of professional actors and voice actors for licensed uses, seems like you could probably find an ethical and cool co-brand opportunity in there.
Have fun building this! It's worth doing.
Wait. You are taking the RF response, sending it up to the cloud to interpret, and then sending the result back? Hard pass from me, sorry. Cool tech, but I don’t want my internal thoughts anywhere near the cloud. Also, this would mean I couldn’t use something like this on the subway when the phone signal goes out intermittently, right?
One thing you might consider is actually telling people what it is on the homepage. Took me a fair bit of work to understand that this is effectively a pair of smart glasses.
Maybe I could have figured that out from the video but for folks who can’t watch the video it’s quite hard to discover what you’re building.
100%, I didn’t watch video or hit reserve button so didn’t realise this was a pair of glasses until I read the text on the HN post
+1 to this
I think this is incredibly cool and straight out of a sci-fi novel! I think this is phenomenal for accessibility and for hands-free computing in general. I also agree with other comments that the website should have more detail on how it works, such as what you included in the post body. Amazing work guys!
Yea in one of the further Ender's Game novels they talk about this tech a lot for characters silently mumbling to the AI.
CMD+F Ender
That's exactly where my mind went. Something I've wanted ever since I read that book a couple decades ago.
Ahhhh exactly! I've wanted this since I was a kid and read those books.
I second that. I've been talking and talking to my phone and AI even more and more since it keeps getting better and is generally pretty accurate these days. And there are times when I end up typing because of environmental reasons.
This is just really groundbreaking and I know the research has been out there for a little while but to actually implement is a whole nother ball game.
I think the use cases for this will expand as the product ships and gets out there!
Agree, incredibly cool, and I could definitely see myself using one, but it does give off slightly dystopian vibes, making me think of the speakwrite in 1984:
"In the long, windowless hall, with its double row of cubicles and its endless rustle of papers and hum of voices murmuring into speakwrites, there were quite a dozen people whom Winston did not even know by name"
Based on my understanding of the technology, this also means you can effectively dictate in loud environments. Correct?
I find that I need this most often when I'm doing yard work, running equipment, or cleaning out the garage. Audio based microphones pick up so much noise.
This is also neat thing to have with people struggling with typing (RSI, injuries, disabilities) but want to do more than just dictation, eg Talon Voice. A common problem with voice commands and dictation alone is that people find they're hurting their vocal chords pretty quickly. Neat.
If the tech is mostly in the glasses temples, I would prefer to have something that attaches to my existing glasses. I have prescription glasses and a big head, tried the Even G2 smart glasses and the available frames set just too small for me
+100 on this! My choice of glasses (and prescription) has nothing to do with my choice of how to talk to my computer. Don't risk failure just because you make them depend on each other.
What you said 100%, we are brainiacs overhere so our CPU is large
This is:
1. Insanely cool
2. Gives me serious "whispering earring" vibes. Imagine having a full on conversation with an AI via subvocalization and listening with ear bud to guide you throughout the day. https://gwern.net/doc/fiction/science-fiction/2012-10-03-yva...
Might not even need buds. I have watched movies on XReal glasses with the sound fairly loud to me next to other people and they didn't notice a thing (I asked them to be sure).
The glasses will have open ear speakers similar to meta glasses! We plan to make our own agent harness and connect it native with the glasses. I have meta glasses but rarely use the AI since it's weird to talk out loud to ask it things when I'm out. This is how we want to solve it
> "you don't actually have to move your lips or even open your mouth for this to work ... It's a bit weird to do"
In the video Dave just finished the training mode and is silently moving his lips, which seems pretty natural to me. I just spent a minute trying to do 'internal speech' (as many elements of speech as possible with lips closed). It does feel weird and seems like internal speech is probably providing a fair bit less signal for the system to sense (in both signal freq and amplitude). I realized I can't guess at how much articulation is 'enough' without feedback.
Based on that I'm guessing adapting to internal speech might follow a bit different path than silent speech, which seems more like 'just do what you already do silently'. Extrapolating, I expect training internal speech might involve more real-time feedback to help the user find the right degree and kind of articulation.
I realize you're still in the prototype phase but I assume an increasing number of people are getting multiple longer sessions. Do new users advance from silent to internal speech quickly and stay there? I'd be surprised as, intuitively, 'Silent -> Internal' seems like a bigger step than 'Normal -> Silent'.
Separately, if I was using it daily, I can imagine wanting to evolve a kind of micro-expression shorthand for 'Yes', 'No', 'Pause' and 'Stop', since two humans naturally evolve similar non-verbal queues over time. Vocalizing words is flexible and expressive but not efficient. It would seem odd if an intelligent, adaptive 'invisible friend' living on my face for years didn't adapt to me and me to it. Are you guys thinking in those directions for the future?
Cue the resurgence of lip reading-based espionage. Imagining having to scan the room for people watching subvocalizers. Will subvocalizers start holding up a clipboard over their face a la NFL coaches?
That's already been a problem ever since people figured out you can recover voice from watching the subpixel vibration of objects within a room. (Video: https://www.youtube.com/watch?v=eUzB0L0mSCI)
There is a reason secure activity happens within secured rooms built to a specific standard https://en.wikipedia.org/wiki/Sensitive_compartmented_inform...
Thought of the same! Cue George Orwell facepalming in his grave.
Do most people talk faster than they can type? It's the opposite for me - I also read aloud slower than I can read in my head.
Most people type at 40-50 WPM. Developers can often type at 70-100 WPM. Meanwhile, most people can talk at 120-200 WPM. Beyond just speed, we've found with many people that talking things out tends to flow more naturally, since it's often a lower friction action so people don't "sanitize" the text in their head before outputting it. Leads to better prompts quite often :)
> talking things out tends to flow more naturally,
I've found the opposite. Typing feels much more "deliberate", and of course you can hit backspace but you can't un-speak a word. With prompting, I've found that, in general, speaking leads to lower-quality results than typing.
I was surprised to find after using dictation heavily all year that I actually talk a load of rubbish when I'm speaking, using all kinds of cliches and fillers and saying way more than was needed.
Yes, I feel very similar. Maybe it's just that my verbal intelligence is lower than average but it feels that the signal to noise ratio is much lower when I speak off the cuff vs when I type.
Same experience. Faster, but also much more filler.
My spouse and I have a rule that if we think a discussion is going to be emotionally charged, we have it over text in different rooms.
It sounds autistic, but writing and reading allow you to be much more precise, careful, and deliberate with your words and helps reduce impulsive outbursts.
This has worked really well for us, as crazy as it sounds.
The bit before your quote was
> with many people
Not everyone. I, at least, definitely overthink what I type, and while I end up with nice-ish sentences in my prompts it takes a lot longer than a train of thought that the AI parses correctly most of the time anyway.
Yes, of course I wasn't trying to speak for everyone. Just my personal experience :)
Also, speech is probably bottlenecked by speed of thought, not making the sounds. I recall some study showing that data rate is pretty consistent between languages, despite wpm varying significantly due to language verbosity. You can try it yourself: try to quickly repeat “one two three four five” then try to read a paragraph out loud as quickly as you can, I bet you can feel the first strain your muscles and the second your brain, and I bet the first blows your typing wpm out of the water.
But what you're calling 'talking things out' I consider to be forming thoughts. I want to do that myself upstream of the LLM. I don't want to pay per token for my half-baked stream of consciousness.
I'm dyslexic and while I can type fairly quickly it's always a struggle to get the spelling and typing mistakes fixed. Talking is a much more natural way to express myself. The frustration of not being able to spell the word that I want doesn't exist. Mis-transcription errors are of course an issue, but those are getting fewer and fewer.
Hard to paste in 2k words of context when you're talking. I don't think voice is the solution for most people who need to communicate heavily with AI.
When I try talking for prompting my coding agents, I'm always severely disappointed with the specificity of the prompt. It's just much easier for me to "talk about" coding specifics with a keyboard than it is for me to speak about them, for some reason.
I suspect this has to do with the nature of the work you're doing; I dunno, just count me firmly in the camp of people who only rarely feel like I can express a thought sufficiently for coding agents with their voice.
I guess it depends on how close to the code you want to work. I find that I lately talk only about the features and UX and can leave the coding details completely to the agent. That might not work in every project, but I suspect it might work more often than people think because it's hard to adapt to the quickly increasing capabilities of LLMs.
I think a good habit is: Try to make the agent fail at least once a week with a too ambitious request. This got surprisingly hard lately :)
Yeah, we have a lot of experience with typing while our eyes and mind are occupied elsewhere. But I've noticed the years have slowed my typing.
I'm the same. I also can think ahead / along much better while typing. When I'm talking I'm just talking, not thinking as much.
But I guess thinking is going out of style anyway.
That said, I know a lot of people prefer talking to their computer, especially when their computer is a phone. So there is definitely a place for stuff like this.
You need to train yourself to speak written speech. When you do that, the thought processes behind typing your words activate, and your language use changes.
As a person who often talks far too fast and incoherently, but types generally fast and legibly, I had never recognised or even considered this, but it seems helpful. Thanks.
Why bother when old ways work _and_ there is no benefit? Or name one.
How?
One approach is reading your and other people's written speech out loud. Pay attention to where it feels awkward; for me, that was the direction I needed to practice. A trick that I use currently to reinforce speaking written speech is using Grammarly to make corrections, which I try to internalize.
Another trick is don't correct words and letters. Say the sentence you really meant to say. It is not uncommon for me to say a thought or a concept two, three, four times in a row as I'm wrestling with what the language should be on the written page.
I talk faster, but beyond the speed, I find it allows me to explain things to the LLM much more naturally.
On my phone, I do. I still like to tap with my thumbs, but my iPhone keyboard sucks so when I need to type a lot, I’d rather dictate.
Most people talk faster than they can type. 80 wpm voice chat is easy for everyone. 80 wpm typing filters out most typists.
This has been an interesting thing for me to watch as it's such a case of people having widely different experiences. I'm sure people that didn't grow up on a keyboard like me can probably talk quicker than they type, but even aside from me being a fairly good typist my speech is held up by being a bit more halting, a bit more of backtracking on word choice, sometimes not quite the same 'voice' of writing as I'm aiming for, all of which obliterates any speed advantage it'd have for me.
But happy to see people get more options.
This reminds me of Eternity's End by Jeffrey Carver and the implants they had. Released in 2000 but the more time goes on the more the neural implant technology is coming about. To be fair I think Enders Game had similar tech to detect subvocal speech like this product.
> This has been an interesting thing for me to watch as it's such a case of people having widely different experiences.
Same. I'm often told I talk too fast, but I feel I communicate slowly because a lot of my fast speech involves halting and backtracking and such.
I can easily type 100WPM+, but I trivially blast out a few paragraphs of perfectly adequate text in a few seconds and then spend a few minutes re-editing it.
Writing also filters the useless crap that is spoken but is not worth writing down.
Yes, I'd estimate the vast majority of people speak faster they can type. Not sure about the thinking part because I usually have 20 threads going parallel in my head and can't imagine what normal thinking would be like.
While sitting at the desk, I type about as fast as I talk. While unloading the dishwasher I'm a much faster talker than typer
I'm not reading aloud most of the time that I'm talking.
For the ones thinking this is great, have you actually tried to talk without making sounds?
I don't think it is an intuitive action at all and I became self-conscious about not making a sound rather than talking like I normally would.
I suppose it would require some "getting used to."
Regardless, I think it is a cool idea and a real problem. Sometimes I don't want to type nor talk out loud so I find myself whispering at my phone like I'm telling it a dirty secret.
--
As I'm writing this, I think this kind of product might not hit the market for consumers, but I'm seeing this used by Flock like companies to spy on people's speech, so kudos on making machine lip reading a thing!
There's already open-source stuff [1][2] out there that can lipread video to transcribe text, but the word error rate is pretty high (and it may not be physically possible to get this down without doing something like subvocal and having other sensors near your face).
1. https://github.com/mpc001/auto_avsr 2. https://github.com/amywork777/lipflow
Have you never talked / mouthed without making sounds? Never even as a kid when something made you mad and you paced around the room think-saying shower thoughts to get back at that person? Even as an adult I probably mouth a sentence or two e.g. "What the fuck is this" when looking at AI output 3-5 times a week
It does feel a little weird to do it voluntarily when not emotional, but that'll be solved as soon as Claude fucks something up :)
First, I absolutely hate having to scroll and scroll and scroll and scroll to try and figure out what's going on.
Second, I read this:
"The current prototypes already decode open-ended silent speech in real time, and accuracy continues to improve as we collect more data and train larger models. Like any input method, it can occasionally get something wrong, so the product is designed to use context and easy corrections rather than pretending errors never happen."
And I have to ask, does this mean everything I vocalize is being sent to an unknown server to be analyzed, potentially read by a person, and then used to train your model further? Because that's clearly not going to fly for either me or my employer. You need to be crystal clear what information people are potentially sharing with you before they purchase your devices.
I remember seeing AlterEgo a few years ago and thinking it was so cool (obviously was missing voice agents to make it really cook)
Was just thinking this could be applicable for people with some disabilities tied to an actual voice agent and speaker. Or even in foreign countries where you talk and respond in the foreign language instead of waiting for an additional translation layer.
I am so glad to see an unpolished early look and an honest evaluation of about five percent error rate in the YouTube video. The really cool stuff will be the applications on top of `subvocal` though at least in my opinion.
So this could take "noise canceling" to a whole new level if you could somehow "speak" across a loud bar or across the world, for that matter. Being integrated into something like Signal or similar end to end encrypted platform would be interesting as well.
Yep, I agree. Noise cancellation is a feature we want to release at some point in the future. Using the RF to denoise a very noisy audio signal which has you speaking in it. And we'll release an SDK as well a few months after shipping to build stuff on top of it!
I'm more looking for the Jane from Speaker for the Dead version. In-ear device that can hear and feel the subvocalization.
I had to look it up, I forgot he communicated with her through sub-vocalizations. I remember the jewel earpiece, but in my head he just communicated through thoughts or something.
Good reference! That series of books Is one of my all time favorites.
First, this my favorite book of all time so I love seeing it shouted out
Second, I agree with exactly this. Something shaped like an AirPod
I mean we're getting pretty close here -- you could have these + your AirPods in transparency mode up and you're not far off. Also Claude won't currently ice you out for going dark, unlike Jane.
With so many people singing the praises of voice to text, I keep thinking about how most sci-fi futures feature subvocalization as a prerec for that kind of adoption. Always love to see sci-fi come to life!
You can have a silent conversation with someone else wearing the device? This does not bode well for casinos.
> This does not bode well for casinos.
For about 15 minutes until they figure out what's going on, take those folks out back and "convince" them to spill the beans on how it work, then come up with a way to detect and prevent it moving forward.
You've been watching too many movies. Casino's are going to risk getting shut down in 2026 to "convince" random people of anything.
A casino would have no problem seeing mouth movement.
Very cool! I was curious to hear the details of how it worked but couldn’t find them on your landing page. I’m glad to see them here and you might want to include them more prominently on the page itself. I didn’t even realize it was a pair of glasses til I read the above.
E.g. your FAQ says it doesn’t use cameras but does not say what it does use. And when I got to the footer and clicked the “how it works” link, it seemingly took me back to the top of the page I had just read.
Can someone comment on the AirPods tweet making the rounds (i.e. the subvocal killer)? I am excited by Subvocal, but am wondering how much bespoke hardware is actually required?
Someone built an open-source version of this, but it’s far from polished:
https://github.com/joeblau/subvox
There was this really interesting one where it reads your lips:
https://github.com/amywork777/lipflow
I’m using these to build my own so I can work in co-working spaces, planes, and libraries. Though moving my mouth with no words might draw some eyes.
Yup we worked with IMUs as well when we started this. They measure aggregated face motion, so cannot distinguish between fine phonetic classes, only broad words. The open source demo got to a 5 word classifier, I believe. We tried a lot to make IMUs work too, in various form factors, but the signal doesn't contain enough information for open ended decoding beyond classifying between a few words. We would have loved to be able to just push software!
> There was this really interesting one where it reads your lips
This is what I thought the original post was about. The glasses you have to wear is where that lost me.
If we could get lip-reading via your computer/phone camera down perfectly, that's the real win. Making people wear your goofy frames is where you lose a massive portion of people. Nobody wants to look like Zuckerberg lol
Lip reading is one of the other modalities we tried as well beyond IMU, EMG and RF! We worked a lot on fine tuning Auto-AVSR, one of the most commonly used open source lipreading models. It's very enticing to work on, since it gets to about 17% word error rate, which looks good enough that you would think working on it further would get it down to product quality, but we found there's an information-theoretic limit on the modality. Speech has 40 phonemes, but only about 12 to 15 visemes (externally visually separable phonetic states). For example P and B look very similar from a camera. This causes the scaling laws on lipreading to flatten out at an error that's too high to be product ready but just low enough to make for a good demo. Our original plan was actually to ship a lipreading software to see if people would want this behavior, but we realized you couldn't make lipreading work!
Now that is insightful! The demo definitely fooled me and even the first repo requires you to train the model.
Lip reading AI would be pretty big since privacy would probably go out the window.
but can't a decision model or some other model deduce "P" or "B" based on the context (i.e., previous words said)?
reminds me of tesla fsd v. waymo. may be a market for both? i.e., camera-only or camera + specific hardware.
Not well enough! You can get to 15-20%ish WER but going beyond that doesn't seem feasible with the info available from a camera, even with a great language model
Why not a pencil in the ear or something you can put in a shirt pocket? Or even earbuds?
Any deaf/HoH person who has tried to do lipreading could have told you all of this too.
Good luck on the project!
I have this problem and I was wondering how it would be solved. For now I can cope because I mostly work from home but I’ll keep track of you guys. Best of luck!
Theres a LOT of people working on this.. Cornell have been putting students on this task for about 5 years.. Lots of fun different ways of doing it. Interesting you went the radar from glasses route.. I wish you well. Yet to see a product apart from the odd lip reading ML project that makes it into a product..
I'm waiting for throat tape a la that one paper where whatever you say in your head translates to micro movements in your throat/jaw or something like that.
Super excited to see more products in this area. I talk to my computer the majority of the time now, and I can do that because I work from home. If I were on public transportation or in an office, it would be much more difficult. It's been interesting to watch the Overton window, if you will, shift for people talking _to_ their phones. Now, the majority of my family will use voice to text on their phone whereas I remember just a few years ago, if not even just a year ago, it was made fun of.
I think these have a place but I can't say the same for most other new AI communication devices. Creeper glasses, pins, watches, desktop units etc. I want to be able to speak and hear from my agents at all times but why would I want a new device when I already wear earbuds? New products are being designed to pick up low murmuring/whispering, like the Subtle earbuds, but I assume most earbuds will be designed this way in future.
I'm curious about whether this could be done with the hardware mounted on top of the laptop screen or on a stand on the desk, rather than the glasses form factor. Have you explored this?
Yes, we have! The same kind of RF doesn't work in that form, since it is attenuated strongly over that big of a distance. But the other interesting alternative we tried it mmWave radar, RF at about 60 GHz, the same band as 5G. This is much more similar to conventional radar, in that it would bounce off the face rather than passing through it like our current system. We found a few problems with this: 1. It faced the same issue as cameras. mmWave radar has a very low penetration in tissue, so it basically just bounced off the mouth. This only let us see visemes, which aren't enough to get to a low error rate as complete phonetic decoding can. 2. While mmWave radar can detect skin movement as small as a few microns via Doppler shift (given it's small wavelength), its spatial resolution with most systems is quite low. For example, it can tell that something moved 2 microns but within a 5cm x 5cm block. This coarse information makes it very hard to decode
That's why we weren't able to make something that can mount to your laptop. We're trying to make a necklace form factor at some point in the future though, but can't give a date on this!
What about something like a baseball cap instead of glasses? Or some sort of head band?
Exploring that too as a next product, but probably a while down the line!
How about a cap with a propellor on it that spins when receiving words :)
One of the coolest things I have recently seen but would love some details. It also got me thinking a about this recent Neuralink post.
https://neuralink.com/updates/72-hour-voice-hackathon/
I would be fairly interested if this works without opening my mouth. Like, if you can nail _micro_ tongue movements, it would feel pretty close to thought.
It actually can! Since the RF can see inside your mouth the system doesn't inherently need lip movements and can be fine tuned on what we call "internal speech". Note that this isn't the automatic tongue movements that occur when "thinking" words to yourself, but it's rather like mouthing with your lips closed. We don't often lead with this since it's weird for many people to do, but with a bit of practice, we have been able to get it down pretty well.
Wow that's fascinating. I've added that bit to your text above - I hope that's ok! It answers what was emerging as a sort of mini-FAQ.
Edit: the more that I think about it the cooler and more important this feature seems!
But how would you distinguish all the sounds that don’t require any tongue movement, like (most of?) the vowels?
Vowels definitely require tongue movement! Leave your mouth closed and whisper "a-e-i-o-u" and you can feel your tongue moving.
Vowels change the shape of your mouth's cavity to change which frequencies to emphasize ("formants") and we hear the differences in vowels by analyzing those formant patterns.
There's subtle changes in internal speech muscles as well often for those kinds of movements, and where it does seem ambiguous language context is usually enough to distinguish
This is very cool, but oddly, the site is TOO focused on the user problem being solved to the extent that it feels like snake oil. The issue is that this is contrary to people's experience of what is possible, so without discussing WHY you can do this, it looks like a scam or vaporware.
Fair feedback, will take into account. Looking to change up the site quite a bit soon!
What I would really like is a washable "cyber suit". Mock or turtle neck (for the voice / STT capture / control), EEG sensors, breathing rate, blood pressure, gestures via arm motion sensors,). Removable rechargeable battery module to wash the torso / shirt slap it on a clean one. For EEG it would have to be pretty compressed though, so not sure it would be comfortable enough to wear to sleep? maybe only an internal harness needs to be that compressed. not sure. I'm tired of wearing a Fitbit, or glasses, or these different things people have to look at, keep up with, break easy etc.
Pretty cool! My only wish is that all this kind of work didn't gravitate toward glasses or assume glasses are the default thing-on-your-face now. 3/4 of humans don't wear them, and even some of us blind bats hate them enough that we endure the hassle of contact lenses!
Should really just be like a leap motion device on the desk, glasses are so gimmicky and aren't gonna fly for people with prescriptions (a large set of people in-front of computers all day)
People with prescriptions can just get versions with prescriptions in them (this is a thing for "smart" glasses already).
Can, but as a new product it is going to limit their adoption rate by some pretty significant amount.
half of the other people in the office in the video are wearing prescription glasses
If no one wants to dictate to their phones or computers in public, surely they don't want to do this (looking like they are talking without making any noise) in public?
Neat! I don't like talking to my computer (audibly or not), but that's a cool demo.
I wonder if we could eventually end up with a "throat muscle" version where people learn to talk a new way without having to move the visible mouth muscles too.
This is amazing, brilliant idea and nice execution. Are you concerned about Meta or any other established smart glasses players potentially copying such an idea?
Are there any associated benchmarks with this? Like how accurate is this technology for different types of facial structures, sentences or languages?
Spent 30 seconds scrolling down to try to figure out what this is. Eventually clicked away from the site because it was taking too long to get to the point. I'm sure it's great and I understand it's something to do with glasses and subvocalizations, but consider a one sentence contextualization at the top of the page.
I was just trying to help a vibe coder and immediately noticed that their README.md was over 2,000 lines long. I asked, "Why is your readme so long?" and their response was, "This is just a really complicated application."
The app essentially manages a bunch of TODO items written in markdown.
For some reason AI coding agents seem to think a README should be a Product Requirements Document (PRD).
I think it's because most projects don't have any settled place (or at least, any place that lives inside the project's source-code repo) to record PRD-like information.
But because AI coding agents really do benefit from having PRD-like info (i.e. a hierarchical breakdown of the "intended what" and "intended how" of the system that "should" exist in the repo, kept updated to reflect changing ideas about those intentions), they really want to record that type of info somewhere, so they can then reference it.
AI coding agents don't seem to have any "taste" (or maybe "confidence"?) when it comes to asserting that even if you don't already have a separate PRD-like file in the repo, you should have one, if you want the agent to do its job well, and so it would request you to let it create one (or just automatically do it.) Instead, they just shrug and cram the PRD stuff into whatever structure you do already have. Which, if you're starting fresh with a greenfield project, is usually just a README.
(I hypothesize that if you tell an AI coding agent to use Behavior-Driven Development [BDD] on a greenfield project, it'll probably lean toward maintaining its PRD-like info in the form of BDD test cases. Haven't tried this experiment yet; would be interested to know the outcome!)
That is exactly what happened in this case; the readme was the PRD.
Throughout the document Claude kept claiming that issues were "mitigated but not fixed". They were essentially bandaid fixes for things it couldn't figure out. When I pointed this out to the author he said, "Well Claude thinks it works."
I wonder what happens to software when enough people try to ship projects like this.
Yup that makes sense. Thanks for the feedback, we'll make some changes shortly!
> Talk without talking. > Input text at the speed of speech, silently and invisibly.
I understood from just this. But the demo video impressed even further.
> Spent 30 seconds scrolling down to try to figure out what this is.
Did you try reading the site? Or maybe doing something other than just scrolling?
Does it need some form of subway surfer to get you to pay attention?
> Eventually clicked away from the site because it was taking too long to get to the point.
So yeah... subway surfer. This generation is cooked.
Really neat tech! Just curious, how much did you leverage AI during the development? This seems like the type of neat tech that we should expect more and more from wielding our new tools well.
this is super cool. I did some digging about current research on avsr using video and lip point cloud movement a while back. found projects like https://github.com/amanvirparhar/chaplin but this seems more promising!
Super cool! love this
I've thought about learning sign language in order to communicate with the computer in a not-super-annoying way. Your solution... much more realistic. Cheers.
Great idea, if only we could use our hands and fingers to input information into the computer
I use the Vekta. I tried whispering and it doesn't feel right.
Throat mics don't work at all - see reviews online.
This is a different approach, so I am cautiously optimistic.
Are there any health risks with this method?
Edit: mostly concerned about RF near my eyes for 8 hours a day.
No, the RF is very low power and can safely be active on your face for long periods. We've done a lot of investigation and verification with safety. While doing R&D the first 2 months we collected hundreds of hours of data on ourselves with various configurations, so we made sure it was safe before :)
Also, the RF transmission only activates when you're actively dictating.
Yeah, so a recent study discovered that talking silently makes other people harder to hear you so they think they have problem hearing.
Sensorimotor debility is a thing. This gadget surely won't help with it.
That is fascinating. How do the radio waves get modulated? Do you think it is possible to use this technique for spying technology, with remote transmitters and receivers intersecting a person's facial anatomy to pick up the details of even a whispered or muttered conversation?
Most probably not possible to do this remotely, since this kind of RF needs to be transmitted through the face, and if you transmit them from too far away very few of them will actually take a path that goes through the face and comes back to your receiver.
They get modulated since your mouth is a complex dielectric environment. Tissue, water, and air have different dielectric constants (different permittivity to RF) and the motion of the muscles in this medium leads to interactions with the waves that fill it, changing their phase and amplitude as they propagate.
So it's a pair of glasses that can transcribe when you mouth words silently? I still don't know how it works, they say no cameras and it works with noise so I assume sort sort of reverse bone conducting?
Says right in the description that they are using radio
The whole paragraph above explains it. Radio through your head.
Category: A product, that's obviously super useful, as long as it will work.
Very cool. I suspect you guys will get scooped up by a bigger player working on smart glasses soon.
I wonder if in a couple of years we gonna have some teeth implant that will capture sounds to our devices.
Great work!
Really like seeing the early prototypes here, and would love to see more on how the RF tech works on the website.
Are you able to patent it?
This is super cool. I think it's the first piece of additional hardware I've even considered pre-ordering.
I did research in this space about eight years ago. Our approach was to look at deformations in the ear canal. Rumor has it that Apple AirPods will have sensors in the ear canal. I was hoping to use those sensors with our app, but it looks like Apple is not going to provide access to the raw sensor data. I expected Apple is going to support subvocal speech pretty soon.
From my understanding decoding via ear deformation requires the mouthing to be quite exaggerated. I am also looking forward to Apple launching it soon though, hopefully it gets more people excited and aware about the category at least
Fantastic!
Just preordered.
What languages do you support? (English is fine, but any others?)
The tech sounds cool, but my guess is this product might work for anyone whose text to command ratio is very high. If the formatting and commanding are the main tasks, then this product would be more of a distraction for a fast typist.
Regarding the website, you should lead with product, its details, rather than founders shown in 360 degrees from various vantage points. It is distracting and frankly irritating.
Just scroll normally!
Reminds me of the Leap Motion I preordered
Does the model require internet access, or is it running entirely locally?
Yes, it requires internet access
God do I hate websites that make you scroll to go through an animation, why do people still do this
Because they don’t even understand their own product well enough to communicate the benefits
It is frustrating and makes me close a lot of sites
If you're selling a physical product, using AI to model your product seems like a really bad idea. You have no idea if the product actually fits on their faces.
Calling it early - this is a scam. There's no way they're going to deliver that product, in that form factor, by Q1 2027.
Why do you hurt communicating your very cool product with an annoying and counter intuitive scroll experience?
And after some time I could not figure out what this is?
Put this part: " building smart glasses that let you talk to your computer without talking out loud. You can mouth words silently and discreetly and the glasses decode them to text at the speed of speech."
right at the top and maybe show someone actually doing that instead of hiding behind cryptic marketing.
Also, the product looks great.
Get your words out of the way 'say what it is'.
Very amazing tech though
That makes sense. We will implement that!
Infuriating website UX, you really must add the scrollbar back. Apple do shiny things like this but they know you can't get rid of the scrollbar and piss people off trying to look at information
Q1 2027- unlikely
“Foundation models” I feel like this has lost all meaning? Can’t you just say “we train models on this data”?
Website is shit, "how it works" tells you nothing much useful about how it works, and I assume there is some custom hardware (as described in the post above) but nowhere on the website I could see this actually said, and therefore zero indication of the size of the interface electronics etc etc
Really cool piece of tech! Languages supported rn? English only?
English only right now, plan to add support for others after shipping
Let's go! Love the idea. Like the analog to bone conduction earbuds. Just please don't turn into WisprFlow where they route the voice metadata, unbeknownst to many, to a third party partner who stores and mines it for who-knows-what. Good luck fellas.
Of course! Privacy is important!
How have the glasses been received? I don't understand why they're required, is it only to have a consistent mount point for the radar sensor, relative to the face? Have you thought about a throat mic?
It looked like there was a throat mic in the first shot... it seems counterintuitive that you'd get better performance out of lidar on face muscles than on a throat mic.
No throat mic, the first image uses EMG (muscle electrical signal) sensors. A throat mic only works if you're still actually whispering (not fully silent) and is also a weird form factor for a consumer device, which is why we didn't go with it!
I'll defer to your expertise on what people find weird, but it seems like you should be able to have a throat-based device that could hide under a shirt collar. I have the Meta Ray Bans and even though I love the functionality, I don't care for the bulky frames. And those are designed by Ray Ban, meaning they're presumably at the upper end of what can be done stylishly.
There is a product by Subtle called Voicebuds that allows for super silent dictation. Looks like the product is not available for purchase yet, but I would prefer to have earbuds over glasses.
https://www.subtle.co
Yup those are pretty cool too! How do you feel about quiet whispering vs completely silent? Genuinely curious we haven't asked too many people
For me: whispering = evolution, silent = revolution. I'd like to see some studies demonstrating its safety.
This is such a weird thing that I can't wait to try it out. I don't know, like it's so crazy that it has to be good
Preordered!
Can we use RF for other medical applications? As an anesthesiologist, we do nerve blocks before surgeries or for pain. One rough indicator that it's working is muscle paralysis. Also similar for botox.
Very interested.
Not sure, but definitely sounds interesting! I do know there was one company trying to use mmWave RF to track patient vitals like breathing patterns and heart rate without having anything hooked up to / touching them
Apple recently a purchased a company with seemingly equivalent technical capabilities:
https://www.cnet.com/tech/services-and-software/apple-qai-ac...
Hope you guys are well-positioned patent-wise.
Yup, Q.ai is different tech and we have our IP :)
They use speckle patterns of a laser shone onto the skin, which is sensitive down to tens of nanometers. Pretty cool tech
Watched the demo video… and if this is satire: incredibly well executed
It's not :)
Much respect for actual innovation. I hope you get filthy rich.
From your comments it seems to reach this point you tried at least open source lip reading software, IMUs, variant antenna mounting strategies, various frequencies, and then gathered training data. You articulated strongly why the product is desirable and why the failed modes were dead-ends. I hope you can deliver on your pre-orders and are able to scale and/or sell the IP for a strong exit.
This is so dumb
There is a long way from a prototype to production. Remember Google Glasses, Oculus, Meta Rayban, Apple Vision Pro?
All of them are visionary and we would think that ppl gonna like them…
Well… ordinary people want boring tech.
This will be similar with whispering to glasses… Visionaries will like it… and return to missionary (boring) s*x (I hope that I don’t get a ban.)
Myself, I would buy these glasses immediately. But I would hate them as well as I would think I am insane (who wants to talk to yourself?).
Edit: Dang replied. I wish all the best to the team behind “whisper glasses”. It is amazing. Connect it with ElevenLabs and you rule the world. (Previous: It wasn’t meant a hate speech.)
(Don't worry, we're not going to ban you.)
A tasteless sex reference is one thing, but shallow-curmudgeonly dismissal of new work is the real sin here!
This wasn’t meant as a hate. Sorry if it sound so. I really like them, I would buy them. Immediately. Sign me in.
But I think (and see) that people prefer boring tech. Whisper glasses is amazing. But most people will probably find it creepy. (Pareto applied.). I hope I am wrong. These guys are like from sci-fi.
I appreciate the kind reply!
A comment like the GP quickly pattern-matches as snark and dismissal because those are so common on the internet. In other words, if you don't intend your comment that way, you need to do something to disambiguate this. Your follow-up comment does this nicely.
The reason this happens is that we all tend to take our intent for granted and forget that it exists in our head and isn't accessible to others unless we make it explicit. https://hn.algolia.com/?dateRange=all&page=0&prefix=true&que...
This also leads to a fascinating (to me at least!) phenomenon where the reply to a moderation comment (i.e. your follow-up here) makes explicit the thought which the commenter meant to communicate. What's fascinating is how different this is from what they originally posted. I call this the rebound effect. https://hn.algolia.com/?dateRange=all&page=0&prefix=true&que...
Cheers. You are absolutely right. After 30 years on the internet I should have known it.
Nobody knows you are a dog. And… don’t make jokes as everybody reads them in different ways…
Talk about over engineering a problem! If typing speed is an issue guess what, humans can train themselves to type really fast on a keyboard.
I think the problem to solve here is repetitive stress injury caused by typing
In this case, I think the problem to solve is ergonomic issues with the keyboards used for typing
They are claiming 200+ wpm on a prototype. Half that speed would put you in the top tier of typists, and the number of people that get anywhere close to 200 is vanishingly small.
It depends on what you’re typing. If you’re coding, it’s probably faster to type `{}[]();|` or 2,450,712 than to say it.
I have some news for you about typing code by hand...
FYI, the subvocal.company site is unscrollable with a mouse wheel in WebKit browsers on Mac (Safari, DDG, Kagi Orion), though the touchpad will work. No issues elsewhere (Mac non-WebKit, Win11, Ubuntu)
Looking into it
this should be fixed now!
Confirmed!
What's wrong with human connection and speaking. :( I feel like the isolation of this modern world is lame.
Maybe you don't want strangers around you hearing you say "Hey Claude wish my grandma happy birthday" as it's not yet morally okay to delegate such social tasks to the models
Aha what a loser thing to do, I personally have a fleet of 347 agents running 24/7 talking to my parents, siblings, grandparents, friends, asking them how they're doing and wishing them a happy birthday when the time comes. I can finally focus on the important things!
Your example proves their point perfectly. You shouldn't delegate wishing your grandma happy birthday to a fucking AI agent. And you should feel ashamed for doing so. And you should feel the social pressure to hide that fact if you do resort to it.
While this tech doesn't feel quite as dystopian as most recent AI innovations, I do think it is a further step in the direction of human disconnection.
As long as the ROI from social relationships(inheritance, friendship favors, dating/mating potential, etc) can be upheld using less effort, such as language models, its a no-brainer and you lose out to competition if you don't do it.
Well you both prove each other’s point ;)
Haha, I can't tell if this is a parody or not
There is no human connection typing words into a box, that's seems like what it's mostly replacing. Talking to your email client, talking to your AI agent. Lots of us are much faster speaking than typing and especially with AI, it doesn't matter a whole lot in my experience how polished the output is, the benefit from ending up with a lot more text because one can just talk freely is very beneficial.
I can see this being useful on public transport where you don't want to bother people while taking notes verbally. It's not all about avoiding connection.
This is more a keyboard killer than a dinner party killer.
This is a little like replying to a show HN for a new kind of stylus input device with “what’s wrong with pen and paper”
All of the images, including the glasses, are AI generated.
Anyone who preorders - you are getting scammed.
Pangram: https://www.pangram.com/history/images/614ffe91-8ba9-4d3c-b1...
They're taking pre-orders. Obviously the product doesn't exist yet. The tech is real.
You can like or dislike generated images (if that's what they are—I haven't looked) but this post has nothing to do with scamming anyone, and given the wealth of technical information in the thread, including a video showing the product under development, that seems like a really weird claim to arrive at.
Et tu, dang?
You don't see how this is misleading or fradulent (i.e. definition of a scam) in any way? A realistic image of someone wearing the glasses that don't exist yet, without disclosing it?
Scam in this context would mean selling people a product or technology that won't ever exist. This is the opposite of that.
If they don't deliver the product in the image they've shown, Q1 2027, will you admit its a scam then? What would it take?
It's absolutely clear that if they're using AI generated images, they haven't even gotten a physical design of the product they're trying to sell.
You're condemning them for spending all their time making the product work instead of...focusing on their website? Bit strange to call someone a scammer for doing the opposite of what scammers do.
I mean the whole website / linked page is filled with AI generated images. Which is one thing. But very basic, obviously AI generated ones, which makes it worse. At least for me it doesn’t inspire confidence.
EDIT: I find talking in that manner in a public setup to be awkward and unpleasant, maybe that's just me.
That said, I think the idea of having a private walkie-talkie that connects on its own frequency for large crowded spaces to be very cool
> I like it but I don't want it, I'm not sure, it feels weird and cringy.
"Please don't post shallow dismissals, especially of other people's work. A good critical comment teaches us something."
https://news.ycombinator.com/newsguidelines.html
p.s. Especially please don't do this when a thread is brand new. Such comments are the easiest to post, and therefore the quickest to appear, but by posting them, you steer the discussion straight away from the curious, thoughtful conversation we want here. Threads are extremely sensitive to initial conditions, so this is important.
Apologies, I edited, can you tell me if my edit is ok? EDIT: happy to delete and repost my edit instead too
It's better. I've turned off the flag.