Open-source local AI that learns how you edit video
Documentary editors spend days hunting through interview footage for the moments that carry the story. Doza Assist does that pass in minutes. Drop in an interview. Get back transcription, story analysis, and a rough cut shaped by your own editing style, not generic AI. Exports to Final Cut Pro, Premiere, and DaVinci Resolve. Runs 100% on your Mac. Nothing uploads to the cloud. Open source on GitHub under MIT license. Signed Mac app shipping soon. Join the waitlist.
Hey Product Hunt 👋
I'm Chris, a documentary filmmaker and editor with 15+ years in the field. I built Doza Assist because I was tired of the worst part of every project: spending days or weeks scrubbing through interview footage hunting for the moments that actually carry the story.
Every editor I know does this same grind. Watch everything. Take notes. Watch it again. Paste transcripts into an LLM. Try to remember where that one perfect soundbite was. It's the bottleneck of every interview-driven project.
So I built the tool I wanted. Doza Assist transcribes your interviews locally on your Mac (no cloud uploads, ever), runs AI story analysis to surface the strongest moments, and exports a rough cut directly into Final Cut Pro, Premiere, or DaVinci Resolve.
The feature I'm most proud of is My Style. You feed the app your finished work and it learns how YOU shape stories. Your pacing, your instincts, your editorial voice. Every suggestion after that is filtered through your style, not generic AI. You can build multiple profiles for different kinds of work.
The whole thing is MIT open source on GitHub. You can clone it and run it today for free. A signed Mac app is shipping soon for editors who don't want to touch a terminal.
I'd love feedback from editors, filmmakers, podcasters, or anyone who works with interview footage. What would make this more useful for your workflow?
GitHub: https://github.com/DozaVisuals/d...
Waitlist for the signed Mac app: https://www.dozavisuals.com/doza...
About Doza Assist on Product Hunt
“Open-source local AI that learns how you edit video”
Doza Assist launched on Product Hunt on April 28th, 2026 and earned 77 upvotes and 6 comments, placing #31 on the daily leaderboard. Documentary editors spend days hunting through interview footage for the moments that carry the story. Doza Assist does that pass in minutes. Drop in an interview. Get back transcription, story analysis, and a rough cut shaped by your own editing style, not generic AI. Exports to Final Cut Pro, Premiere, and DaVinci Resolve. Runs 100% on your Mac. Nothing uploads to the cloud. Open source on GitHub under MIT license. Signed Mac app shipping soon. Join the waitlist.
On the analytics side, Doza Assist competes within Productivity, Open Source, GitHub and Video — topics that collectively have 762.1k followers on Product Hunt. The dashboard above tracks how Doza Assist performed against the three products that launched closest to it on the same day.
Who hunted Doza Assist?
Doza Assist was hunted by Chris Cardoza. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of Doza Assist including community comment highlights and product details, visit the product overview.
Chris Cardoza