AI video editing for documentary & film editors
search terabytes, find the story, assemble faster
EditAssist helps documentary and film editors search across hundreds of hours of footage, build narrative assemblies from transcripts, detect scenes, and conform locked cuts to camera originals. All local, so sensitive archive material never leaves your machine.
Pain points
Searching hundreds of hours
Describe what you need in plain English and find it across terabytes in seconds. 'Find every mention of the river' or 'pull every emotional reaction from the contributors' returns ranked results with timecodes.
Narrative assembly from transcripts
Build thematic assemblies, chronological string-outs, or narrative arcs from transcripts and paper edits. The agent matches scene descriptions to the best takes and adds markers.
Archive & sensitive material
All indexing and transcription runs on your own GPU. No footage is uploaded. Archive material, contributor interviews, and sensitive rushes stay completely private.
Conform to camera originals
Auto-conform the locked cut to camera originals, validate every relink, and render broadcast masters, DCP, and textless versions for international distribution.
Prompts
“We shot 400 hours for this documentary. Find every mention of the river and build a thread.”
“Build a narrative structure from the interviews: group by theme, not chronology.”
“Identify recurring visual motifs across the whole film and create a supercut.”
“Pull every emotional reaction from the contributors and rank them by intensity.”
“Map every location mentioned in the transcripts and cluster the footage by geography.”
“Build a paper edit of the 3-hour assembly: keep only the strongest narrative beats.”
“Transcribe all 60 interviews, identify the 12 key characters, and build a selects reel per person.”
“Conform the locked 8-episode series to 8K ARRIRAW originals and validate every relink.”
Features
Semantic archive search
Search by visual description, transcript phrase, speaker, or emotional tone across terabytes of footage without manual logging.
Narrative assembly
Build thematic, chronological, or narrative structures from transcripts, scripts, and paper edits with frame-accurate timeline mapping.
Scene detection & chaptering
Auto-detect shot boundaries, scene changes, and chapter breaks. Cross-reference against scripts to flag missing coverage.
Local & secure
All transcription, vision analysis, and indexing runs on your own machine. No footage uploaded. No cloud dependency.
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 solutions: AI video editing for video agencies, AI video editing for corporate video, AI video editing for course creators. Or see everything EditAssist connects to.