Natural language video editing
describe the cut, get the timeline
Edit video by describing what you want in plain English. EditAssist understands natural language commands and operates DaVinci Resolve, Premiere Pro, After Effects and Final Cut directly. No scripting, no macros, no memorising shortcuts.
Workflow
Type or speak what you want: 'build a rough cut from today's interview footage, colour-match to episode 3, and sync the external audio'. EditAssist parses the intent, plans the steps, and executes them inside your NLE. It handles the transcription, the search, the assembly, and the conform in one continuous workflow.
The agent understands context across the project. Ask for 'the best reaction shot of the interviewer' and it knows which camera angles cover the interview, which takes are clean, and where to place the cut. It learns from your corrections and can save repeatable workflows as skills.
Prompts
“Build a rough cut from today's interview footage, colour-match to episode 3, and sync the external audio.”
“Build selects from scene 14, prioritising takes the director marked.”
“Trim every clip on V1 to remove the first and last two seconds of each take.”
“Compare the current cut to yesterday's version and show me what changed.”
“Build an assembly from the shooting script: match each scene description to the best take.”
“Build a timeline from the storyboard: one shot per panel, with placeholder durations.”
“Add the voice-over recording to V2 and time it to the existing picture edit.”
“Detect every jump cut in the interview and smooth them with cutaways from the B-roll.”
Features
Intent parsing
Natural language commands are translated into multi-step editing plans. No scripting or macro knowledge required.
Context awareness
The agent understands project structure, camera angles, transcripts, and previous edits. It reasons about coverage and continuity.
Skill automation
Save repeatable workflows as skills that prep projects, build standard assemblies, or deliver to your house spec with one command.
Local-first privacy
All transcription, vision analysis, and search indexing runs on your own machine. Only chat text leaves the device.
Local-first
All transcription, vision analysis, semantic search, and clustering run on your own GPU. Nothing about your footage is uploaded. The only data that leaves is the text of your conversation with the agent. It's free to download, local models are free, and a new account starts with £15 of credit and no card. For long-running cloud work, pay as you go, or choose £20/mo Starter or £100/mo Pro.
Getting started
- 01Download EditAssist for macOS or Windows and create an account. You get £15 credit and no card is needed.
- 02Ingest your footage. The agent transcribes, indexes, and clusters automatically.
- 03Describe what you want in plain English and let the agent build the cut.
- 04Review, refine with conversational commands, and export to your delivery spec.
More tools: AI video editor, Rough cut generator, Auto clip generator. Or see everything EditAssist connects to.