SPEECH & CAPTIONS
Video to Text Transcription
Word-timed transcripts you can search, edit, cut from and turn into captions.
- Plan
- Every plan, Hobby (free) included
- AI credits
- 5 credits to transcribe a file the first time; reusing that transcript is free.
What it does
Vidmoat transcribes your footage with a speech model and returns every word with its start and end time. The transcript is cached per file, so captions, Text Mode and filler removal all reuse it without paying again.
Transcription runs on our servers (Cloudflare Workers AI, with our own server as the fallback). Media that only exists in your browser is transcribed in the browser instead, with an English-only model.
How to use it
- Add your clip to a project.
- Open Text Mode from the More menu, or add captions, and the transcript is made.
- Read, search and fix the text, or turn it into captions in one click.
Who it is for
- Podcasters and interviewers
- Educators making accessible video
- Editors who search footage by what was said
Questions about Video to Text Transcription
Where is my audio processed?
On Cloudflare Workers AI, with Vidmoat’s own server as the fallback. Our privacy notice lists every processor.
Do I pay again for captions after transcribing?
No. The transcript is cached per file, so captions and cleanup reuse it for free.
What if a clip has no speech?
If no words are found, the credits are refunded.