I always wanted to do 2 things and never found enough time
* ballroom dance competition videos to share on insta for peers and judges
my kid is doing ballroom dancing and as a dance parent i record every competition, but i always struggle to find time to edit it well to share it.
I end up with a lot of high quality videos from my sony a6700 or iphone 17 and do some editing with resolve but it takes FOREVER and so i do it rarely
* Travel videos to share with friends and colleagues
I love travelling and this summer i have hiked through Albanian Alps and Dolomites and wanted to stitch those into a cool video to showcase to my friends and coworkers, but i just dont have enough time.
I have a lot of high res videos on my Iphone 17, Insta360 x5 and DJI Avata 2 that i have no time to edit.
My dream would to unleash my agents on these huuuge files and to help me organize them by time, and place and then to use agents to pick out the best scenes per place and help me stitch great showcasing videos
Does anyone have a good workflow for these? Would Kino be a great tool or is this best done locally with Claude/Codex?
Amazing! That's very similar to what I do in Kino whenever i shoot in Log. We support very dense MP4 files, ProRes, many different cameras that were filming at the same time, etc.
When you sign in there is a workflow button to click on where you just plug in your iPhone, your SD cards, and it will index everything + lay out a quick stringout that makes sense. It helps to also give links to instagram videos whose style you like. Tons of friends are now using us to edit home movies they never would have otherwise, as the footage was just sitting there earlier
Truly amazing work Luke and team! Been following Kino for a while now and just looked at your website (a lot better than prev!) the other day.
I'm also working on an agentic video product (chatoctopus.com), and I can tell how hard it is compared to what influencer of X (Opus made it in an hour, etc) make it seem like. They don't tell how many times they corrected it, how long it took, and how much it cost.
You are one of the four YC companies I know of (Cardboard, Palmier, and Motion/Mosaic being other three) working on that, so I keep visiting occasionally to see if I can get "inspired" by something new.
Thanks for the kind words! A new user who has also trudged through these many new "agentic editors" said that the following things set Kino apart in his mind (copying this over from his message):
- True multiplayer Google Docs like editing, which legacy NLEs haven’t done particularly well
- Integrated review and feedback
- Support for local media, which a lot of cloud editors lack
To support the above we needed to build beyond just a single player editor that agents love. All the infrastructure for collaboration, storage, and complex projects had to come too.
The local scrub plus cloud render split is the part I would poke at first. I build a desktop video editor on my own, and the bug class that has cost me the most time by far is the preview and the export disagreeing. Two decode paths, two color assumptions, and a frame that looked right on the timeline comes out shifted in the file.
Mine broke on something small. A Display P3 tagged still looked right on the timeline and came out different in the file, because the preview path and the export path handled the color tag differently. Nobody notices until they open the finished export. How are you keeping the proxy scrub and the final render honest with each other?
Unlike other tools that bring video editing to the browser, we render locally and let you scrub your original footage! The proxies are for your teammates who want to see what you see, but they can also get the original footage through Kino's storage
Splendid effort and I'm so glad actual industry experts built something like this than someone like me who is just a vibe-coder. Industry experience counts for so much in such cases. One thing I didn't see and I really hope you'll incorporate it is templates. I did a lot of podcasts two years ago with various guests and every podcast was intended to follow the same format, same title design, intro music, trailer clips etc as well as cut clips for social media. If all these preferences can be fed into a template then, the agent can make realtime decisions on each video and work long horizon and output a full production with just a few commands each time. That, for me, would be the holy grail if backed up by an agent guided template builder. Something to think about.
Thank you! We have templates at https://kino.ai/templates, which we're adding onto every week. You can also ask the agent to take what went well during a project and turn it into a template for next time.
A user just tried this recently! Right now I'd just feed a huggingface model url and Kino will try it out on your footage in a way that can be undone / modified.
We are supporting more and more models natively (voice healing, scene edit detection, rotoscoping) given how annoying it can be to manually download local models or set up your own cloud inference. There isn't a great open source Mac option for this one so we're prioritizing!
Great potential, wishing you the best. How fast are the exports? Opus 5.5 was taking around the same time as actual video time to export in my tests. Did you find a way to solve this on a real time timeline like this?
Thanks! Exports render locally, and Kino often beats real-time on lighter timelines. We hit about real-time as well for timelines with heavy footage. Beat it via parallelization and better use of your hardware is important to us but not the current priority.
Used Kino yesterday head to head with claude-code directly to make a simple video. Kino was way easier to nudge and control. Props to you guys for building something that "just works". You rarely see that when you try anything in software.
When we started it was just Remotion, but yes tons of other options have exploded onto the scene. Long-term we want to be as zen as possible, where Opus 5.5 and its successors make graphics and edit videos in whatever form hobbles them the least. So far, Remotion has allowed us to achieve WYSIWYG editing while also handling very complex timelines with heavy duty media formats
OP can add their answer but I'm also in the same boat (building chatoctopus.com) and would say Remotion is well-established as a video framework and also has a lot better support for infra/rendering. Rendering takes a lot of time and Remotion's Lambda fanout is amazing for speed up.
Others feel vibe-coded (looking at you hyperframes), and LLMs have to learn their syntax from scratch. X influencer forget to tell you how slow your output would be.
So am I understanding that Kino is most effective when you already have assets, not necessarily for starting from scratch? Because I mostly use Claude nowadays to put little explainer videos together either for myself or my teammates. Doesn't seem Kino is the right match for that, unless I'm missing something.
Kino works from scratch as well, it's just that supplying your company url or past work lets you get a win quite quickly. I'd still recommend Kino for your use case since we offer a UI to quickly nudge your agent and give feedback and a single place for all these videos to live
Legit question - have you used this with adult content? It would be interesting to be able to create compilations and also cut longer content down into clips for small / individual studios or cam models.
This is awesome.
I always wanted to do 2 things and never found enough time
* ballroom dance competition videos to share on insta for peers and judges
my kid is doing ballroom dancing and as a dance parent i record every competition, but i always struggle to find time to edit it well to share it.
I end up with a lot of high quality videos from my sony a6700 or iphone 17 and do some editing with resolve but it takes FOREVER and so i do it rarely
* Travel videos to share with friends and colleagues
I love travelling and this summer i have hiked through Albanian Alps and Dolomites and wanted to stitch those into a cool video to showcase to my friends and coworkers, but i just dont have enough time.
I have a lot of high res videos on my Iphone 17, Insta360 x5 and DJI Avata 2 that i have no time to edit.
My dream would to unleash my agents on these huuuge files and to help me organize them by time, and place and then to use agents to pick out the best scenes per place and help me stitch great showcasing videos
Does anyone have a good workflow for these? Would Kino be a great tool or is this best done locally with Claude/Codex?
Amazing! That's very similar to what I do in Kino whenever i shoot in Log. We support very dense MP4 files, ProRes, many different cameras that were filming at the same time, etc.
When you sign in there is a workflow button to click on where you just plug in your iPhone, your SD cards, and it will index everything + lay out a quick stringout that makes sense. It helps to also give links to instagram videos whose style you like. Tons of friends are now using us to edit home movies they never would have otherwise, as the footage was just sitting there earlier
Truly amazing work Luke and team! Been following Kino for a while now and just looked at your website (a lot better than prev!) the other day.
I'm also working on an agentic video product (chatoctopus.com), and I can tell how hard it is compared to what influencer of X (Opus made it in an hour, etc) make it seem like. They don't tell how many times they corrected it, how long it took, and how much it cost.
You are one of the four YC companies I know of (Cardboard, Palmier, and Motion/Mosaic being other three) working on that, so I keep visiting occasionally to see if I can get "inspired" by something new.
Thanks for the kind words! A new user who has also trudged through these many new "agentic editors" said that the following things set Kino apart in his mind (copying this over from his message):
- True multiplayer Google Docs like editing, which legacy NLEs haven’t done particularly well
- Integrated review and feedback
- Support for local media, which a lot of cloud editors lack
To support the above we needed to build beyond just a single player editor that agents love. All the infrastructure for collaboration, storage, and complex projects had to come too.
The local scrub plus cloud render split is the part I would poke at first. I build a desktop video editor on my own, and the bug class that has cost me the most time by far is the preview and the export disagreeing. Two decode paths, two color assumptions, and a frame that looked right on the timeline comes out shifted in the file.
Mine broke on something small. A Display P3 tagged still looked right on the timeline and came out different in the file, because the preview path and the export path handled the color tag differently. Nobody notices until they open the finished export. How are you keeping the proxy scrub and the final render honest with each other?
Unlike other tools that bring video editing to the browser, we render locally and let you scrub your original footage! The proxies are for your teammates who want to see what you see, but they can also get the original footage through Kino's storage
Splendid effort and I'm so glad actual industry experts built something like this than someone like me who is just a vibe-coder. Industry experience counts for so much in such cases. One thing I didn't see and I really hope you'll incorporate it is templates. I did a lot of podcasts two years ago with various guests and every podcast was intended to follow the same format, same title design, intro music, trailer clips etc as well as cut clips for social media. If all these preferences can be fed into a template then, the agent can make realtime decisions on each video and work long horizon and output a full production with just a few commands each time. That, for me, would be the holy grail if backed up by an agent guided template builder. Something to think about.
Thank you! We have templates at https://kino.ai/templates, which we're adding onto every week. You can also ask the agent to take what went well during a project and turn it into a template for next time.
Any chance for a feature that corrects eye contact when reading from a teleprompter? ie. https://www.descript.com/eye-contact https://docs.nvidia.com/nim/maxine/eye-contact/latest/overvi...
A user just tried this recently! Right now I'd just feed a huggingface model url and Kino will try it out on your footage in a way that can be undone / modified.
We are supporting more and more models natively (voice healing, scene edit detection, rotoscoping) given how annoying it can be to manually download local models or set up your own cloud inference. There isn't a great open source Mac option for this one so we're prioritizing!
Great potential, wishing you the best. How fast are the exports? Opus 5.5 was taking around the same time as actual video time to export in my tests. Did you find a way to solve this on a real time timeline like this?
Thanks! Exports render locally, and Kino often beats real-time on lighter timelines. We hit about real-time as well for timelines with heavy footage. Beat it via parallelization and better use of your hardware is important to us but not the current priority.
Fair enough thanks!
Used Kino yesterday head to head with claude-code directly to make a simple video. Kino was way easier to nudge and control. Props to you guys for building something that "just works". You rarely see that when you try anything in software.
Thank you so much! Please let us know if you run into any friction or places where Kino still gets stumped
Why did you choose Remotion vs other solutions (there's like 3-4 other now, including one from HeyGen)?
When we started it was just Remotion, but yes tons of other options have exploded onto the scene. Long-term we want to be as zen as possible, where Opus 5.5 and its successors make graphics and edit videos in whatever form hobbles them the least. So far, Remotion has allowed us to achieve WYSIWYG editing while also handling very complex timelines with heavy duty media formats
OP can add their answer but I'm also in the same boat (building chatoctopus.com) and would say Remotion is well-established as a video framework and also has a lot better support for infra/rendering. Rendering takes a lot of time and Remotion's Lambda fanout is amazing for speed up.
Others feel vibe-coded (looking at you hyperframes), and LLMs have to learn their syntax from scratch. X influencer forget to tell you how slow your output would be.
Let's go Luke! Been a fan since the Blue Haus summer! Super pumped
So am I understanding that Kino is most effective when you already have assets, not necessarily for starting from scratch? Because I mostly use Claude nowadays to put little explainer videos together either for myself or my teammates. Doesn't seem Kino is the right match for that, unless I'm missing something.
Kino works from scratch as well, it's just that supplying your company url or past work lets you get a win quite quickly. I'd still recommend Kino for your use case since we offer a UI to quickly nudge your agent and give feedback and a single place for all these videos to live
AI videos are decidedly not Kino.
Legit question - have you used this with adult content? It would be interesting to be able to create compilations and also cut longer content down into clips for small / individual studios or cam models.
Good stuff!