Comments
Hacker News
Nice project. I’m building a similar project. It’s open source too.
https://github.com/DonkeyUseCorp/Donkey
It’s mostly a web app with a native swift companion app to access local resources like TTS, file storage and video rendering.
I arrived at the same conclusion as you; every app should have AI chat. Just give it full access to the app like a real user. I found that users prefer talking to the AI when editing vs clicking around.
by dthedavid
Nice! Because the Grok subscription is the cheapest-per-second video offering (that I'm aware of) but doesn't provide API access, I'm often moving between the browser and editor (typically Final Cut).
It feels cheaper by orders of magnitude right now per-second. I'm not sure how long that will continue, but until then, that's pretty important to me, especially when video generation is so imprecise, and thus more of a "rough draft" creative tool than a "final shot" tool.
Quite often my workflow looks like: "Grab this frame from which I'd like a continuation" -> "Upload back to Grok on web" -> "Generate until happy" -> "Download and use".
So a feature request (or I'll just fork next time I'm doing something with AI video) is simply a browser tab alongside the generation tab, literally just to make that window swapping easier, and ideally with 'download' pointing to a sensible location to avoid file replication.
This feels closest to how I use AI video, which is just kind of like an infinitely extensible library tab on my video editing software. I know you said 'no webview' - I don't know Swift well enough to know if that excludes this feature.
There's probably a bunch of ways to improve my specific flow once there's a browser within the UI, especially with MCP integration. Much to consider.
And overall it looks fun, and I'm excited to give it a try. It's great this has beat detection specifically, because that's non-negotiable in a video editor for me when doing AI stuff, as the medium remains more suited to non-dialogue work.
Similarly, the CapCut 'AI video editor' that's most similar to the 'MCP' feature is unusably chaotic, so I'm interested to see how well models do in your architecture. I can understand why you've found structures like 'beat' or 'transcription' massively aid it.
Final Cut export - if it isn't supported by what you've already done (I don't move stuff between editors much!) - is really useful to me personally also.
Best of luck! Excited to test it! Thanks for sharing.
Well Plamier Por was mac native, but it did inspired me to build FableCut: https://github.com/ronak-create/FableCut
by ronak_parmar
Great project!
have you considered giving the agents code-based video rendering like MoviePy or Remotion? Since LLMs are mostly trained on texts and code maybe for edits use code based approach and for complex scenes fallback for seedance, elevenlabs mcp or connectors
by k_dev
I've been following Marcos's youtube channel and it's so great to see that they've finally found their thing. Looks like an awesome product that people actually want. Well done.
This is what I have been waiting for in order to process my massive action camera library, I will definitely give it a try!
I will start with older standard GoPro videos, and hope that by the time I make it to the Insta360 videos the editor supports 360 video (unless it does already!)
by nsbk
> Most work in the editing workflow is more mechanical than creative.
I really disagree with this. Maybe once you start producing videos with a formula, it's true. But if you stop to think about it, a lot of things that people consider gruntwork hide little decision in them that subtly influence the creative process.
A lot of tech-minded people don't understand this about art but after editing tens of thousands of photos and over 300 videos, I can't say that there is much mechanical in the process. By automating parts of the process with AI you do hide some of the subtle decisions that might even be subconscious and therefore it still destroys creativity.
I'm sad when someones makes a product like this. Because what happens is that creativity is claimed as something important when really in the long run it is just suppressed for the sake of more efficiency.
I don't expect many people to care to understand this because there's $$$ in front of them and technologically-minded people get a dopamine hit from tech but that's the way it is and you can't hide from that truth. Sooner or later such things as this will be seen as an immense folly.
by vouaobrasil
This looks great! Have you thought about dropping the 'subscription'-part and 'just' selling credits instead?
Here's my thinking as a SaaS founder: when I launch a product, I don't need a video every month. So a monthly pricing makes me do this little calculation every time: "do I need a video this month? nah. Then I'll wait. I lose the early-bird price, but I still net out cheaper." And since there's no yearly option, there's nothing pulling me into the early plan either.
What I would jump on is a launch offer. Something like XXX credits for a good price, enough that it feels like 3 videos over the course of a year. Even if I never use them all (very likely, honestly), I'd buy it. Credits sit there and wait for me, a subscription just quietly bills me for months I don't need it.
Hope that makes sense :)
by Marciplan
Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- Nice project. I’m building a similar project. It’s open source too.
https://github.com/DonkeyUseCorp/Donkey
It’s mostly a web app with a native swift companion app to access local resources like TTS, file storage and video rendering.
I arrived at the same conclusion as you; every app should have AI chat. Just give it full access to the app like a real user. I found that users prefer talking to the AI when editing vs clicking around.
by dthedavid - Nice! Because the Grok subscription is the cheapest-per-second video offering (that I'm aware of) but doesn't provide API access, I'm often moving between the browser and editor (typically Final Cut).
It feels cheaper by orders of magnitude right now per-second. I'm not sure how long that will continue, but until then, that's pretty important to me, especially when video generation is so imprecise, and thus more of a "rough draft" creative tool than a "final shot" tool.
Quite often my workflow looks like: "Grab this frame from which I'd like a continuation" -> "Upload back to Grok on web" -> "Generate until happy" -> "Download and use".
So a feature request (or I'll just fork next time I'm doing something with AI video) is simply a browser tab alongside the generation tab, literally just to make that window swapping easier, and ideally with 'download' pointing to a sensible location to avoid file replication.
This feels closest to how I use AI video, which is just kind of like an infinitely extensible library tab on my video editing software. I know you said 'no webview' - I don't know Swift well enough to know if that excludes this feature.
There's probably a bunch of ways to improve my specific flow once there's a browser within the UI, especially with MCP integration. Much to consider.
And overall it looks fun, and I'm excited to give it a try. It's great this has beat detection specifically, because that's non-negotiable in a video editor for me when doing AI stuff, as the medium remains more suited to non-dialogue work.
Similarly, the CapCut 'AI video editor' that's most similar to the 'MCP' feature is unusably chaotic, so I'm interested to see how well models do in your architecture. I can understand why you've found structures like 'beat' or 'transcription' massively aid it.
Final Cut export - if it isn't supported by what you've already done (I don't move stuff between editors much!) - is really useful to me personally also.
Best of luck! Excited to test it! Thanks for sharing.
- Well Plamier Por was mac native, but it did inspired me to build FableCut: https://github.com/ronak-create/FableCutby ronak_parmar
- Great project! have you considered giving the agents code-based video rendering like MoviePy or Remotion? Since LLMs are mostly trained on texts and code maybe for edits use code based approach and for complex scenes fallback for seedance, elevenlabs mcp or connectorsby k_dev
- I've been following Marcos's youtube channel and it's so great to see that they've finally found their thing. Looks like an awesome product that people actually want. Well done.
- This is what I have been waiting for in order to process my massive action camera library, I will definitely give it a try!
I will start with older standard GoPro videos, and hope that by the time I make it to the Insta360 videos the editor supports 360 video (unless it does already!)
by nsbk - > Most work in the editing workflow is more mechanical than creative.
I really disagree with this. Maybe once you start producing videos with a formula, it's true. But if you stop to think about it, a lot of things that people consider gruntwork hide little decision in them that subtly influence the creative process.
A lot of tech-minded people don't understand this about art but after editing tens of thousands of photos and over 300 videos, I can't say that there is much mechanical in the process. By automating parts of the process with AI you do hide some of the subtle decisions that might even be subconscious and therefore it still destroys creativity.
I'm sad when someones makes a product like this. Because what happens is that creativity is claimed as something important when really in the long run it is just suppressed for the sake of more efficiency.
I don't expect many people to care to understand this because there's $$$ in front of them and technologically-minded people get a dopamine hit from tech but that's the way it is and you can't hide from that truth. Sooner or later such things as this will be seen as an immense folly.
by vouaobrasil - This looks great! Have you thought about dropping the 'subscription'-part and 'just' selling credits instead?
Here's my thinking as a SaaS founder: when I launch a product, I don't need a video every month. So a monthly pricing makes me do this little calculation every time: "do I need a video this month? nah. Then I'll wait. I lose the early-bird price, but I still net out cheaper." And since there's no yearly option, there's nothing pulling me into the early plan either.
What I would jump on is a launch offer. Something like XXX credits for a good price, enough that it feels like 3 videos over the course of a year. Even if I never use them all (very likely, honestly), I'd buy it. Credits sit there and wait for me, a subscription just quietly bills me for months I don't need it.
Hope that makes sense :)
by Marciplan