Hi all. Thanks for the interest. I'm going to post an impromptu blog post here just explaining what this is. The rather unfortunate ground stop today made this unexpectedly useful with the pilots here on Orcas just to get a sense of the chatter in our airspace re the situation.
This is an ETTUS B210 attached to a dual 4090 box. It's a polyphase channelizer that takes the entire airband, channelizes it using cuda code on GPU, demodulates it, detects transmissions, throws away data tx and then feeds the tx through a voice model I created for transcription. A separate LLM reads the transcriptions to create a situational awareness picture of the airspace.
I'm interested in open sourcing this and making it available for folks who can run an ETTUS B210 or high quality SDR with enoguh bandwidth and a local GPU machine, so that we can cover more airpsace.
This was born out of an incident we had not too long ago where a pilot around KORS (based at Friday Harbor) lost the engine in his 172, and put it in the water in front of a ferry and was picked up by the ferry. We're a pretty close bunch on Orcas Island and we only heard about it days later via social media. That felt completely unacceptable, and I set out to create a radio that could monitor everything in real-time, all the time, and alert on emergencies. That has extended to transcribing and creating situational awareness for a chunk of airspace.
I'm an IFR pilot. I fly a T206H regularly in IMC around here and I'm a ground instructor. You can email me at mark@defiant.com or find me on x at mmaunder if you'd like to connect. I'm particularly interested in hearing from folks who can run a station on their own hardware and are under bravo or a charlie or even just somewhere interesting re airspace.
Edit: OMG I just realized who you are. I used to read your blog obsessively before I became a pilot, and while I was working heavily on mysql. Thanks for that!!
> That felt completely unacceptable, and I set out to create a radio that could monitor everything in real-time, all the time, and alert on emergencies.
I just want to send a heartfelt thank you. My sister and her family live on Orcas, and my mom flies in on Kenmore every couple months, as she is too old to make the long drive. I often worry about the the whole thing, and track the flight on Flightradar24. I have watched too much Juan Brown.
From a tech pov, this is cool as heck. From a you are helping watch my mom on somewhat sketchy flights in case I am not available pov: I would like to really thank you for choosing to do this with your time and money.
To get at that, I would love a mayday/pan-pan type alert subscription system. Do you currently have a system for handling the fastest time to alert? Or, is this only retrospective currently? Or, have I missed something entirely?
Thanks that's very kind of you. Please make sure they know about the mercy flight program on the island.
It's real-time data and yes I'm adding in alerting. Right now I'm focused on improving the voice model and the AI part that processes it's output and once I get to place where I'm confident in its reliability, I'll add in alerting. Should be a few days.
First, What an amazing project!
> a voice model I created for transcription.
>> The model is outstanding. I literally spent 5 minutes listening and barely understood most of the comms, the model was extremely helpful. This looks frontier/next level. Is it possible to share how you built this model/tips&trixjs?
I have questions! Does it really require all that hardware? I've spent the last week working on a P25 scanner with 2 RTL-SDRs on a Pi and transcription running on a Ryzen AI laptop. The Pi keeps up with recording fine but it is only 4-5Mhz bandwidth instead of the ~11Mhz you're monitoring. For me transcription only lags by a few seconds but if I ran it on my desktop with a 2080ti it wouldn't even be that much.
What STT model are you using? In my tests I've gotten the best WER with whisper v3 large but it's still not that good.
I would expect that the hardware involved is massive overkill.
The Ettus SDRs are very nice and are marked up enormously over the BOM cost. You’re paying for an integrated, supported system, with good engineering, not for the parts. These days, for this particular use, you could probably build your own direct (no downconversion) receiver with a decent filter and, say, a 400MSPS DAC. (This was not a thing at any reasonable price point 15 years ago when I last played with this stuff.) Or you can buy or build a little mixer and choose an appropriate LO frequency and use a much cheaper DAC. Or you can buy a cheaper SDR.
~15 years ago I amused myself for about an hour using a USRP (older Ettus gear) and MATLAB to do more or less this but for regular FM radio, one channel at a time, on a decent laptop of the era. The processing power needed to channelize and demodulate a few channels from I/Q data is very, very low. Even coming up with some kind of optimal demodulation scheme wouldn’t use many cycles. (Although I suspect that there is more space to try to jointly optimize demodulation and transcription with FM than with AM.)
It would be a fun project to try to kludge up an ESP32 of some sort to do this. The tricky bit would be that the WiFi/BT hardware doesn’t go to DC.
i'm amazed at the transcription quality here. i spent a couple minutes listening, just in awe at the often nearly unintelligble crackling over the speakers, and then a half second later it prints a transcription that seems totally plausible to what i just heard, but without the transcription i don't think i would have been able to understand it.
I've honestly never understood how pilots or the tower are able to understand anything that's happening over the radio. Not only is there always constant static and interference, but they all speak in short rapid fire bursts that even beyond the lingo and shorthand is hard to process. I'd never be able to get a pilot's license.
90% of radio communications is standard and expected.
If I get the call sign and a few key words, I can normally figure it out. For the most part you kinda know what people are gonna say before they say it, or at least have it narrowed down to just a few possibilities. You also just get an ear for the narrowband AM sound after a few hours.
“(Garbled) n123a (garbled) joining (garbled) one three” heard at an untowered field is going to be “local traffic, Cessna N123a is joining the downwind leg for runway 13.”
Or if you’re on final approach and the tower calls you up, there are really only a few things they are going to tell you, most likely is “Cessna 123a cleared to land”.
Plus, I’m guessing you have o my listened to very busy feeds at commercial airports. Students at smaller airports will often announce that they are a student, and controllers and other pilots will try to slow it down and give them a little extra room and time.
No idea how AI does it, but I assume it’s not too hard since there are essentially unlimited hours of recording to train on.
In the air it’s usually way more clear than the stuff you hear on liveatc etc. if I’m 5k above terrain, have a nice radio and antenna, I have a solid 50+ mile range with anything local being quite clear. Ground recorders have way worse reception unless someone rented space on a tower.
!! That's awesome, I'm across the water in Port Townsend & have been playing around with a pair of RTL-SDR's doing something similar with police & SAR bands. this is awesome work man.
ps: grew up in obstruction pass, I suspect we have some friends in common. Nice work dude.
Very nice! We just started building something similar for our SAR team so we could scroll back and look at any pertinent Sheriff/Fire/SAR transmissions we have missed or mis-heard.
The voice recognition model on Adrian's thing is amazing.
I wonder if you can partner with ham radio enthusiasts running their own Web SDRs… maybe have a way to point a pipeline at a websdr. Some of em do have air band.
These are raw transcripts unedited by me that I extracted possibly related to the groundstop, generated at time of posting:
2143Z, 126.400 Victoria Ground (weak signal): "Yeah, we just uh communication issues, so we got the traffic stopped on [unintelligible]"
2151Z, 134.800 Vancouver Centre, pilot of a flight ending "364": "We're saying they just have an alternate plan. They've been getting lower and lower 48 right now. We're on
the phone with you, they are saying cannot show any reason why we would be out of communication to Seattle. So just otherwise we do have some alternates that we're talking
about, but we just want to see, you see anything on your end that we cannot proceed to Seattle?"
2152Z, 134.800 Vancouver Centre, same pilot: "Okay, sounds good. Yeah, we appreciate that. We'll be staying by and we'll just kind of get the alternate plans for ready to
go. Thank you."
2159Z, 121.075 Victoria Terminal, controller: "Seacraft 304, just a heads up here, there is a ground stop for an aircraft about into Vancouver at this time. I'm sure you
have a VFR slot, seeing where you're headed there now, so I'd like to be still going to take you, but it just has stopped that you might end up getting turned around."
2159Z, 121.075 Victoria Terminal, controller: "Sorry, that's all inbound aircraft, ground stop."
2200Z, 121.075 Victoria Terminal, controller: "Yeah, it's not affecting anything airborne at this time. We're just about departing anything for Vancouver and Calgary at this
time."
2201Z, 126.400 Victoria Ground, pilot (weak signal): "Hey Ground, it's Jazz 270, and I'm guessing there's a flow for Vancouver."
2203Z, 121.075 Victoria Terminal, pilot: "Uh just wanted to confirm uh there's a ground stop uh going into Vancouver on this frequency?"
2203Z, 121.075 Victoria Terminal, controller: "Encore 3325, that's correct. Nothing is departing to land at Vancouver at this time."
2204Z, 134.800 Vancouver Centre, pilot: "Yeah, right now they said normal ops continue, but we'll see what happens once we get closer."
2217Z, 126.125 Vancouver Departure, pilot: "Yeah, you guys not having any of the issues that they're having in the US right now?"
2217Z, 126.125 Vancouver Departure: "Uh, apparently the ones uh seeing ground stop for the 14 major airports I've just got a few minutes. Okay, thanks."
2227Z, 126.400 Victoria Ground, pilot: "Encore 58, information Papa, requesting flow through to Vancouver for 2255." Reply: "Roger, 2255 on the flight plan."
This reminds me of a Claude hobby project from a while back that listens on public KiwiSDR receivers (on-demand, politely, never taking the last slot) and decodes ships’ DSC radio signals: https://research.datadesk.eco/skywave/
These are mostly quite boring, but I did manage to make some progress in triangulating position between multiple receivers using the delay, which would be useful as a method for tracking AIS-dark vessels.
ohhhh, I was wondering why selecting a frequency wouldn't show the number of comms that matched the count on the left-hand side. Turns out the squelch setting filters the ones out below threshold.
While scanning through frequencies, I found it a bit annoying to have to unclick the previous frequency to exclusively see the new frequency but I got the hang of it.
Would be nice to have a "jump to time" button so when you search for something, you can immediately get the before/after context rather than manually input the date/time. For now, I learned to copy link and load that.
Encore keeps getting transcribed as "anacortes" heh...
Also, the recordings you hear online will often be more garbled (weaker signal) than what you hear in the cockpit or what ATC hears, because (1) in the air you have clear line of sight to the ground transmitter and to other planes, and (2) ATC has receivers that are designed to be able to cover the area they're controlling.
Ah this is such a hot debate in the community. Yes it's straight up AM simplex and the argument for is: With AM when you step on another tx it screeches. Also pilots can hear pilots to improve situational awareness vs duplex which would have pilots only hearing ATC. Huge legacy fleet of aircraft. Cost to upgrade anything in a certified aircraft. There are so many arguments for digital though. it's a tough one.
You get used to it. There's like three things you're likely to hear based on context, and deciding which one it was isn't too difficult. Discerning additional detail and nuance (left/right on course) then becomes a much lower cognitive load. It is definitely a learned skill, but it comes automatically with time.
There's also the accessibility case, as its quite common for people to have wildly different abilities in auditory discrimination, including auditory processing disorders. That's probably a big reason why people have such differences of opinion of how bad they perceive the problem to be. Its likely such a selective pressure on the industry that a number of people just don't stick around because of it, so the industry likely undercounts it.
Any kind of auditory discrimination challenge someone has will lead to much higher cognitive load to interpret noisy transmissions. That cognitive load is a resource that could be better spent on other flight instruments and crisis situations.
Putting a design lens on, someone with APD an extreme user who, if properly made accessible to, would wind up improving everyone's experience not just their own.
I wonder if a switch to digital could keep transmitting on analog for legacy needs while having a second digital system be the primary one used.
The counterpoint to that is that for the same SNR where you're at barely (or not at all) audible or garbled on analog, you have absolutely clear digital audio.
Yeah, and with most comms being stereotyped, most messages carry little data, meaning you can easily add redundancy and still take up the same or less airtime. You will still need plaintext messages for complex situations, but even that can be transmitted more clearly and efficiently with digital encoding.
with digital you can utilize the bandwidth much better thanks to compression.
you can also load up on error correction to such an extent that what would have been completely garbled analog audio would instead result in crystal clear digital.
and this ignores the potential for a secondary ultra low bandwidth transcription text stream that would play back with TTS if all else fails.
the real reason this hasn't happened is backward compatibility hell and regulation up the wazoo. there isn't going to be much money to be made in pioneering this, a tiny startup that may wish to serve this tiny market would take one look at the regulation and nope out.
I’m supposed to be flying tomorrow afternoon for my wedding next week. I fly to Toronto and then Mexico, so no stops in the US but needless to say I’m worried.
Not trying to promote myself, but there's another project I created to provide pilots with IFR situational awareness so we know if there's going to be a ground delay when we call for clearance. It's a bit technical, but you can use it to check your own route. It's at https://ifrmeter.com/
Yeah sorry about that. This is a software defined radio based on a hangar at Orcas island, receiving the entire airband, channelizing it into over 700 channels, and then demodulating the channels and playing whatever is sent provided it's voice. It also transcribes using a voice model and an LLM parses the output and attempts to create cards on the right hand side. It's also trying to detect simulcasts and remove the duplicate transmissions. Hope that helps explain it. It's also archiving everything so you can listen to old transmissions. Right now I'm working to keep the server up. Thanks HN. :-) For context, I'm a pilot based at KORS and a nerd.
I don't think GP is confused about the technical details, they are confused about what they are looking at and what the point is. I think the answer they were looking for is (correct me if I'm wrong) "this is a live feed of transcribed ATC comms in the Vancouver area," and possibly some evidence that there is a ground stop since things seems to be running as normal based on the most recent logs.
Haven't listened by KORS is a small untowered airport in the San Juan islands, in the northwest corner of WA state. It's very near Victoria, Canada, whose ATC controls the nearby airspace, extending into US territory slightly.
The post title is implying that Victoria airport is also subject to a ground stop.
This post is referring to Victoria, Canada. The website, Orcas Airband, has radio traffic from a bunch of stations around the Salish Sea (Victoria, Seattle, Vancouver, Nanaimo...); orcas are like a mascot of this part of the world.
AFAICT, while there are many, many places named after Victoria, none of them are in California.
I hate this AI web-style, can't the people behind these websites alter the prompts so that the UI looks a little bit less AI-ish? I've started to miss the brutalist style, if that's even possible.
Hi all. Thanks for the interest. I'm going to post an impromptu blog post here just explaining what this is. The rather unfortunate ground stop today made this unexpectedly useful with the pilots here on Orcas just to get a sense of the chatter in our airspace re the situation.
This is an ETTUS B210 attached to a dual 4090 box. It's a polyphase channelizer that takes the entire airband, channelizes it using cuda code on GPU, demodulates it, detects transmissions, throws away data tx and then feeds the tx through a voice model I created for transcription. A separate LLM reads the transcriptions to create a situational awareness picture of the airspace.
I'm interested in open sourcing this and making it available for folks who can run an ETTUS B210 or high quality SDR with enoguh bandwidth and a local GPU machine, so that we can cover more airpsace.
This was born out of an incident we had not too long ago where a pilot around KORS (based at Friday Harbor) lost the engine in his 172, and put it in the water in front of a ferry and was picked up by the ferry. We're a pretty close bunch on Orcas Island and we only heard about it days later via social media. That felt completely unacceptable, and I set out to create a radio that could monitor everything in real-time, all the time, and alert on emergencies. That has extended to transcribing and creating situational awareness for a chunk of airspace.
I'm an IFR pilot. I fly a T206H regularly in IMC around here and I'm a ground instructor. You can email me at mark@defiant.com or find me on x at mmaunder if you'd like to connect. I'm particularly interested in hearing from folks who can run a station on their own hardware and are under bravo or a charlie or even just somewhere interesting re airspace.
That's so cool... I'm a pilot (have 3 planes) and would be interested in hosting one--or just running for my own edification, really.
I'll message you.
Awesome. Thanks.
Edit: OMG I just realized who you are. I used to read your blog obsessively before I became a pilot, and while I was working heavily on mysql. Thanks for that!!
> That felt completely unacceptable, and I set out to create a radio that could monitor everything in real-time, all the time, and alert on emergencies.
I just want to send a heartfelt thank you. My sister and her family live on Orcas, and my mom flies in on Kenmore every couple months, as she is too old to make the long drive. I often worry about the the whole thing, and track the flight on Flightradar24. I have watched too much Juan Brown.
From a tech pov, this is cool as heck. From a you are helping watch my mom on somewhat sketchy flights in case I am not available pov: I would like to really thank you for choosing to do this with your time and money.
To get at that, I would love a mayday/pan-pan type alert subscription system. Do you currently have a system for handling the fastest time to alert? Or, is this only retrospective currently? Or, have I missed something entirely?
Thanks that's very kind of you. Please make sure they know about the mercy flight program on the island.
It's real-time data and yes I'm adding in alerting. Right now I'm focused on improving the voice model and the AI part that processes it's output and once I get to place where I'm confident in its reliability, I'll add in alerting. Should be a few days.
First, What an amazing project! > a voice model I created for transcription. >> The model is outstanding. I literally spent 5 minutes listening and barely understood most of the comms, the model was extremely helpful. This looks frontier/next level. Is it possible to share how you built this model/tips&trixjs?
I have questions! Does it really require all that hardware? I've spent the last week working on a P25 scanner with 2 RTL-SDRs on a Pi and transcription running on a Ryzen AI laptop. The Pi keeps up with recording fine but it is only 4-5Mhz bandwidth instead of the ~11Mhz you're monitoring. For me transcription only lags by a few seconds but if I ran it on my desktop with a 2080ti it wouldn't even be that much.
What STT model are you using? In my tests I've gotten the best WER with whisper v3 large but it's still not that good.
I would expect that the hardware involved is massive overkill.
The Ettus SDRs are very nice and are marked up enormously over the BOM cost. You’re paying for an integrated, supported system, with good engineering, not for the parts. These days, for this particular use, you could probably build your own direct (no downconversion) receiver with a decent filter and, say, a 400MSPS DAC. (This was not a thing at any reasonable price point 15 years ago when I last played with this stuff.) Or you can buy or build a little mixer and choose an appropriate LO frequency and use a much cheaper DAC. Or you can buy a cheaper SDR.
~15 years ago I amused myself for about an hour using a USRP (older Ettus gear) and MATLAB to do more or less this but for regular FM radio, one channel at a time, on a decent laptop of the era. The processing power needed to channelize and demodulate a few channels from I/Q data is very, very low. Even coming up with some kind of optimal demodulation scheme wouldn’t use many cycles. (Although I suspect that there is more space to try to jointly optimize demodulation and transcription with FM than with AM.)
It would be a fun project to try to kludge up an ESP32 of some sort to do this. The tricky bit would be that the WiFi/BT hardware doesn’t go to DC.
Is P25 not encrypted?
It can be. My local network has a few encrypted talkgroups for more sensitive stuff but most is not.
i'm amazed at the transcription quality here. i spent a couple minutes listening, just in awe at the often nearly unintelligble crackling over the speakers, and then a half second later it prints a transcription that seems totally plausible to what i just heard, but without the transcription i don't think i would have been able to understand it.
Now I wonder if it can transcribe Cradle of Filth - Funeral in Carpathia?..
I've honestly never understood how pilots or the tower are able to understand anything that's happening over the radio. Not only is there always constant static and interference, but they all speak in short rapid fire bursts that even beyond the lingo and shorthand is hard to process. I'd never be able to get a pilot's license.
"Delta blarg-mumble-twenty-blurgle-fargle-*screeeeeeeech*eading-foxtrot-squidgle-skee thanks."
It's absolutely amazing that the AI model is able to transcribe all that noise.
90% of radio communications is standard and expected.
If I get the call sign and a few key words, I can normally figure it out. For the most part you kinda know what people are gonna say before they say it, or at least have it narrowed down to just a few possibilities. You also just get an ear for the narrowband AM sound after a few hours.
“(Garbled) n123a (garbled) joining (garbled) one three” heard at an untowered field is going to be “local traffic, Cessna N123a is joining the downwind leg for runway 13.”
Or if you’re on final approach and the tower calls you up, there are really only a few things they are going to tell you, most likely is “Cessna 123a cleared to land”.
Plus, I’m guessing you have o my listened to very busy feeds at commercial airports. Students at smaller airports will often announce that they are a student, and controllers and other pilots will try to slow it down and give them a little extra room and time.
No idea how AI does it, but I assume it’s not too hard since there are essentially unlimited hours of recording to train on.
i'm guessing the model is doing something similar, and has a fairly confident set of the possible phrases to map sounds to.
I spent a good 10 seconds chuckling at your very apt portrayal there.
In the air it’s usually way more clear than the stuff you hear on liveatc etc. if I’m 5k above terrain, have a nice radio and antenna, I have a solid 50+ mile range with anything local being quite clear. Ground recorders have way worse reception unless someone rented space on a tower.
Well timed! SSL cert date 2026-11-12?
!! That's awesome, I'm across the water in Port Townsend & have been playing around with a pair of RTL-SDR's doing something similar with police & SAR bands. this is awesome work man.
ps: grew up in obstruction pass, I suspect we have some friends in common. Nice work dude.
Same here in Seattle area; but I believe PSERN is flipping on encryption like yesterday so I completely abandoned working on something similar.
Very nice! We just started building something similar for our SAR team so we could scroll back and look at any pertinent Sheriff/Fire/SAR transmissions we have missed or mis-heard.
The voice recognition model on Adrian's thing is amazing.
Thanks! I visit Spruce Goose a lot. Yum! My wife and I are friends with some folks in your neighborhood. You Port Townsenders are cool!
I wonder if you can partner with ham radio enthusiasts running their own Web SDRs… maybe have a way to point a pipeline at a websdr. Some of em do have air band.
cool stuff!
These are raw transcripts unedited by me that I extracted possibly related to the groundstop, generated at time of posting:
If you scroll back to 2:03pm (the time this link was posted) there was this interaction:
14:03:04 Uh just wanted to confirm uh there's a ground stop uh going into Vancouver on this frequency?
14:03:10 Encore 3325, that's correct. Nothing is departing to land at Vancouver at this time.
This reminds me of a Claude hobby project from a while back that listens on public KiwiSDR receivers (on-demand, politely, never taking the last slot) and decodes ships’ DSC radio signals: https://research.datadesk.eco/skywave/
These are mostly quite boring, but I did manage to make some progress in triangulating position between multiple receivers using the delay, which would be useful as a method for tracking AIS-dark vessels.
ohhhh, I was wondering why selecting a frequency wouldn't show the number of comms that matched the count on the left-hand side. Turns out the squelch setting filters the ones out below threshold.
While scanning through frequencies, I found it a bit annoying to have to unclick the previous frequency to exclusively see the new frequency but I got the hang of it.
Would be nice to have a "jump to time" button so when you search for something, you can immediately get the before/after context rather than manually input the date/time. For now, I learned to copy link and load that.
Encore keeps getting transcribed as "anacortes" heh...
Cool stuff!
Is CA for Canada or California?
Victoria, BC, Canada
Right?
Surprised at how garbled many of these transmissions come across.
I can barely understand 50% of what is being said and am impressed by these professionals who can.
Are the transmissions still analog for security / interoperability reasons?
Also, the recordings you hear online will often be more garbled (weaker signal) than what you hear in the cockpit or what ATC hears, because (1) in the air you have clear line of sight to the ground transmitter and to other planes, and (2) ATC has receivers that are designed to be able to cover the area they're controlling.
Ah this is such a hot debate in the community. Yes it's straight up AM simplex and the argument for is: With AM when you step on another tx it screeches. Also pilots can hear pilots to improve situational awareness vs duplex which would have pilots only hearing ATC. Huge legacy fleet of aircraft. Cost to upgrade anything in a certified aircraft. There are so many arguments for digital though. it's a tough one.
You get used to it. There's like three things you're likely to hear based on context, and deciding which one it was isn't too difficult. Discerning additional detail and nuance (left/right on course) then becomes a much lower cognitive load. It is definitely a learned skill, but it comes automatically with time.
There's also the accessibility case, as its quite common for people to have wildly different abilities in auditory discrimination, including auditory processing disorders. That's probably a big reason why people have such differences of opinion of how bad they perceive the problem to be. Its likely such a selective pressure on the industry that a number of people just don't stick around because of it, so the industry likely undercounts it.
Any kind of auditory discrimination challenge someone has will lead to much higher cognitive load to interpret noisy transmissions. That cognitive load is a resource that could be better spent on other flight instruments and crisis situations.
Putting a design lens on, someone with APD an extreme user who, if properly made accessible to, would wind up improving everyone's experience not just their own.
I wonder if a switch to digital could keep transmitting on analog for legacy needs while having a second digital system be the primary one used.
You can still understand a noisy analogue transmission. With digital you get it or you don't.
The counterpoint to that is that for the same SNR where you're at barely (or not at all) audible or garbled on analog, you have absolutely clear digital audio.
Yeah, and with most comms being stereotyped, most messages carry little data, meaning you can easily add redundancy and still take up the same or less airtime. You will still need plaintext messages for complex situations, but even that can be transmitted more clearly and efficiently with digital encoding.
with digital you can utilize the bandwidth much better thanks to compression.
you can also load up on error correction to such an extent that what would have been completely garbled analog audio would instead result in crystal clear digital.
and this ignores the potential for a secondary ultra low bandwidth transcription text stream that would play back with TTS if all else fails.
the real reason this hasn't happened is backward compatibility hell and regulation up the wazoo. there isn't going to be much money to be made in pioneering this, a tiny startup that may wish to serve this tiny market would take one look at the regulation and nope out.
Only ground stop is the FAA one: https://spaces.navcanada.ca/workspace/ois/
OG scanner transcriber https://scanner.rachelbythebay.com/
I’m supposed to be flying tomorrow afternoon for my wedding next week. I fly to Toronto and then Mexico, so no stops in the US but needless to say I’m worried.
Not trying to promote myself, but there's another project I created to provide pilots with IFR situational awareness so we know if there's going to be a ground delay when we call for clearance. It's a bit technical, but you can use it to check your own route. It's at https://ifrmeter.com/
I'm confused by this one, when I click the link I am seeing a lot of live traffic?
EDIT: The title is confusing to read, there's 2 statements.
Yeah sorry about that. This is a software defined radio based on a hangar at Orcas island, receiving the entire airband, channelizing it into over 700 channels, and then demodulating the channels and playing whatever is sent provided it's voice. It also transcribes using a voice model and an LLM parses the output and attempts to create cards on the right hand side. It's also trying to detect simulcasts and remove the duplicate transmissions. Hope that helps explain it. It's also archiving everything so you can listen to old transmissions. Right now I'm working to keep the server up. Thanks HN. :-) For context, I'm a pilot based at KORS and a nerd.
I don't think GP is confused about the technical details, they are confused about what they are looking at and what the point is. I think the answer they were looking for is (correct me if I'm wrong) "this is a live feed of transcribed ATC comms in the Vancouver area," and possibly some evidence that there is a ground stop since things seems to be running as normal based on the most recent logs.
Yes, that's it!
What SDR did you use that has the bandwidth to capture the entire airband? You need to scan about 20MHz for the voice channels.
What STT system / model are you using?
I had a plan to try something like this from where I live, but I wasn't sure how to solve those two problems.
If you're trying to build something that integrates with the Linux desktop, check out dabri https://github.com/AshBuk/dabri
Not mine, I just found it 2 hours ago.. No mention of it on HN so not sure what others think about it.
He listed some technical details here: https://news.ycombinator.com/item?id=50491176
No, there are no ground stops at yyj. All flights operating normally and no notams.
If someone who understands what this is feels like explaining it, that would be very cool :)
Please see my other reply. Happy to answer any questions in between trying to keep the server running. Amazing how well node performs under load.
Ok, thanks for that!
Haven't listened by KORS is a small untowered airport in the San Juan islands, in the northwest corner of WA state. It's very near Victoria, Canada, whose ATC controls the nearby airspace, extending into US territory slightly.
The post title is implying that Victoria airport is also subject to a ground stop.
There's a Victoria in California? That's nearly as confusing as Ontario, CA.
This post is referring to Victoria, Canada. The website, Orcas Airband, has radio traffic from a bunch of stations around the Salish Sea (Victoria, Seattle, Vancouver, Nanaimo...); orcas are like a mascot of this part of the world.
AFAICT, while there are many, many places named after Victoria, none of them are in California.
That's why movies open with shots of the Eiffel tower and subtitle 'Paris, France'.
What model are they using for the speech to text transcription?
This is a _sick_ tool. I can imagine using this for listening to all sorts of mixed streams.
This is very nice, I always wanted something like this.
I hate this AI web-style, can't the people behind these websites alter the prompts so that the UI looks a little bit less AI-ish? I've started to miss the brutalist style, if that's even possible.