The multicam that cuts itself to whoever's talking.
Speaker Cut reads every camera's mic, switches the edit to whoever's speaking, transcribes every word, and hands back a finished Final Cut timeline — in minutes, on your Mac.
Drop a multicam. Get a finished edit.
Three steps, one round-trip through Final Cut. No plugins, no timeline scrubbing.
Drop your multicam
Export XML from Final Cut and drop the .fcpxml — bundle, zip, or the Info file inside. Speaker Cut reads each camera's isolated mic to know exactly who's talking. No diarization, no guesswork.
It cuts to the speaker
Per-mic voice detection follows the conversation — the video switches to whoever's speaking, holds through pauses, and cuts wide on overlaps. Audio is leveled to −16 LUFS, and every word is transcribed with click-to-jump timecodes.
Notes, highlights & export
With Speaker Cut One or Pro, AI pulls your best highlights and cold-open hooks — rate them, lock keepers, re-roll the rest. Then bundle the FCPXML, transcript & notes into one zip, or import straight back into Final Cut.
Everything a talking-head edit needs.
Any number of cameras
Two speakers or a ten-person panel — as long as each has an isolated mic, on-device voice detection attributes every line without cloud diarization.
Word-perfect transcript
Every line attributed to the right person. Click any timecode to jump the Final Cut playhead right to that moment.
Loudness-matched audio
Two-pass loudnorm to −16 LUFS, true-peak safe — every speaker sits at the same level, no clipping.
AI highlights & hooks
Share-ready clips and cold-open soundbites, pulled from the transcript. Rate, lock, and re-roll until they're right.
One-click export package
FCPXML, a Notes & Highlights PDF, transcript PDF and SRT — bundled in a single zip to hand your editor.
Private by design
The cut, transcript and leveling run entirely on your Mac. Your footage is never uploaded anywhere.
Film to a camera, record to a recorder.
Final Cut syncs every camera and external recorder into one multicam by their audio — so Speaker Cut can detect each speaker on their clean recorded track while cutting the video to their camera. Set each lane's Audio and Video independently: a webcam does both, a field recorder is audio-only, a silent camera is video-only.
Free to cut. Pay only for the AI.
The app, the speaker-cut, the transcript and the export are free forever. AI show notes and highlights are the paid layer — buy it once, or subscribe.
Speaker Cut
The full editing engine. No account, no key.
- {c}Auto speaker-cut multicam
- {c}Full transcript + SRT
- {c}Loudness-matched audio
- {c}Export package for Final Cut
- {x}AI notes & highlights
Speaker Cut One
Unlock AI for good. On-device free, or your own key.
- {c}Everything in Free
- {c}AI show notes, highlights & hooks
- {c}Free on-device AI (macOS Tahoe)
- {c}…or bring your own Anthropic / OpenAI key
- {c}Licensed for one Mac — move it anytime
Speaker Cut Pro
Zero setup. We host the best cloud AI for you.
- {c}Everything in Free
- {c}Hosted premium AI — no key
- {c}Works on any macOS, no Tahoe needed
- {c}Generous monthly generation quota
- {c}Licensed for one Mac — move it anytime
One-time and subscription both unlock the same AI features — pick how you'd rather pay.
Good to know.
Does it work with Final Cut Pro?+
Do I need an internet connection or an API key?+
Is my footage uploaded anywhere?+
I'm not on macOS Tahoe yet. Can I still use the AI?+
How does licensing work across my machines?+
Stop cutting multicams
by hand.
Download Speaker Cut free and turn your next interview into a finished edit before your coffee's cold.