Turn any video into editable, timestamped text
Upload MP4, MOV, WebM or MKV video and get a speaker-labeled transcript you can edit, search and export as TXT, DOCX, SRT or VTT.
Availability depends on the configured speech provider.
Guest preview: up to 50 MB and 10m. Results are kept for a limited time unless you create an account.
VoqText extracts the speech track from your video, normalizes the audio and sends it to the configured speech engine. You get paragraphs with start times and detected speakers, synced to a player so you can click any line and jump to that moment.
Nothing is burned into the video: the transcript lives beside the original file in your private workspace, where you can correct it, rename speakers and export captions or documents.
What you get
- Timestamped paragraphs synced to video playback
- Speaker labels you can rename or merge
- An editor with undo, redo and revision history
- TXT, DOCX, SRT, VTT, JSON and CSV exports
Who it is for
- Creators quoting recordings in blog posts and captions
- Teams archiving webinars and product demos as searchable text
- Students converting recorded lessons into notes
Frequently asked questions
Which video formats can I upload?
MP4, M4V, MOV, WebM and MKV are accepted. The file is validated by its actual content, not its extension, and must contain an audio track.
Do I need an account to try it?
No. Guests can transcribe one short file per time window and read a real excerpt of the result. An account keeps the project and an eligible plan unlocks the full transcript, editor and exports.
How long does it take?
Usually well under the length of the recording, but it depends on file size, queue load and the speech provider. Progress is shown live on the job page.