AI video editing for podcast editors
cut episodes faster with transcript-driven editing
EditAssist helps podcast editors turn long recordings into tight episodes and social clips. Transcribe locally, cut from the transcript, remove filler words, label speakers, and export audiograms or vertical Shorts. Your audio never leaves your machine.
Pain points
Hours of raw audio to trim
EditAssist transcribes every word locally and lets you cut by selecting text. Changes propagate to the timeline instantly, so you can rough-cut a 90-minute episode in minutes.
Filler words and dead air
The agent detects ums, ahs, breaths, and long pauses, then tightens the timeline with clean crossfades. You set the threshold; it does the surgery.
Speaker attribution
Automatic speaker diarization labels every voice in the episode. Build speaker-specific selects, normalise levels per person, and export attributed transcripts.
Social clip extraction
Find the best soundbites, auto-reframe to vertical, burn captions, and export TikToks, Reels, and Shorts from the same episode in one batch.
Prompts
“Find the three best interview soundbites under 15 seconds.”
“Build an audiogram for the best 60 seconds of this episode.”
“Detect every time I talk over my guest and flag it.”
“Normalise all dialogue to -14 LUFS.”
“Find all clips where dialogue overlaps between two speakers.”
“Create waveform audiograms for the 5 best quotes from this week's episode.”
“Remove all filler words from the guest's answers but keep the natural pauses.”
“Tighten every interview clip by removing dead air and breaths between sentences.”
Features
Local transcription
Whisper-based models run on your own GPU. No audio uploaded. Multi-language and speaker-label support.
Text-to-timeline editing
Cut, reorder, and delete by editing the transcript. Every text change maps to frame-accurate timecode.
Silence & filler removal
Auto-detect and remove dead air, filler words, and breaths with adjustable thresholds and clean crossfades.
Vertical batch export
Export 9:16, 1:1, and 4:5 versions with burned captions across all social specs in a single command.
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 YouTubers, AI video editing for social media teams, AI video editing for course creators. Or see everything EditAssist connects to.