Hi HN,
Build this tool in a couple of hours with OpenAI Codex to scratch an itch.
As part of my videos workflows I needed to cut the videos myself since the agent is pretty bad cutting and timing using only the transcription. But using a big app like Premiere or DaVinci Resolve was overkill so I used Astra to build an app tailored to that very task.
It will be useful to others with the same problem.
Tested only on Silicon Macs, so any feedback is welcome.
As part of my workflow when the agent get the video it can open the app with the video or videos loaded in the timeline for me to cut and then export the cuts in a format the agent can use and continue the workflow.
As an old FCP person, this has scratched my brain too, Davinci seems to be furtherst along on the MCP race.
Tying your tool out and gather up some feedback!
Thank you, for testing and the feedback.
Smooth experience, quick launch! most of my manual things I still feel more comfortable in FCP, though and the agentic run I'd like to keep fully in text form! I'll run some more tests and keep ya posted. Good job!
Speed and Performance was one of the things I wanted to have.
FCP is great for all sorts of things needed when editing video.
fastCutVid is only for cutting source footage and then continue the agent workflow.
Was a Premiere user since version 4 onwards. But right now the heavy weight on the video workflows is done by agents; the only part I need to edit is the cut.
Thanks for taking the time and for your feedback :)
excited to test it, great idea
I had a similar idea for an opensource video editor where you edit along side the LLM but I gave up on it haha
Glad you like the idea. Right now is only an editorial step for automatic video processing/editing workflows. But I will love to hear what ideas you have for: editing alongside LLMs.
https://github.com/ucsandman/Magnetic
honestly this was in June which feels like forever ago and I'm not entirely sure what my plan was haha. I knew I was going to be doing marketing for my projects and thought an editor with LLM capabilities would make it easier, but then I just made a repo and a skill where agents can make marketing material directly
https://github.com/ucsandman/marketing-studio
Thanks for sharing.
Looking at your projects brought a couple things to my mind. I use the agent to make the initial cuts removing silence, etc, from the transcript; so when the project is loaded it already is "half" baked. Then I just need to adjust the cut.
Do have a similar marketing workspace for my projects, one for each, with a abstract repo that have all skills and brand assets, tone of voice etc. By starting a new project the new workspace initialize by interviewing the user to gain all information of the project/product and then start defining assets, tone of voice, workflows, etc. Been using that for several month now, it gets better as the models get better.
Wondering what I need to adjust to open source it...
[dead]
[flagged]