LUMIÈRE
Lumière · Tools
Every word, on the record.
Somewhere in hour two, someone says the line the whole piece needs. Every word your footage says, time-stamped to the frame and labelled by speaker — ready to read, search, export, or cut on.
How it works
Three steps. No timeline required.
- 01
Upload your footage
Video or audio, long or short. Interviews, rushes, recordings — the engine takes it as it is.
- 02
We transcribe it
Word-level timestamps and automatic speaker detection across the whole recording. Who said what, and exactly when.
- 03
Use it your way
Download the transcript or subtitle files — or stay in the suite and cut the video by editing its words.
What you get
Built in, not bolted on.
-
Word-level timestamps
Not per-sentence guesses — every single word carries its own time, accurate enough to cut on.
-
Speaker detection
Who said what, labelled automatically across the whole recording.
-
Transcript & subtitle export
Take the text with you as a transcript or as timed subtitle files.
-
Feeds the whole suite
The same transcript powers subtitles, translation, dubbing and text-based editing — transcribe once, use everywhere.
Accuracy depends on your audio. Clean speech transcribes very well; a noisy room still deserves a human read-through — which is why every word stays editable.
One suite, every tool
The same engine, other doors.
Each tool here is the same production suite, entered where you need it. Start with one; the rest is already there.