Translate an uploaded video or audio file

Upload a file you own for a timestamped transcript, search and original-language SRT/VTT. Translation is available only when configured for your language pair.

See how VTI works

Personal testing · closed beta

Built for media that was never published

Interview recordings, camera and phone footage, voice notes, webinar captures, screen recordings, archived material. If it is yours and it is not on a platform with a caption track, there is nothing for a native tool to work from.

VTI processes authorised uploads into transcripts. Translation requires an enabled provider and supported language pair.

Supported formats and limits

VTI accepts:

What you get back

For each uploaded file:

Supported languages

Transcription languages are listed below. Translation availability depends on the configured provider and language pair:

Pricing

Plans and quotas are read from the live configuration of this deployment:

Paid plans are not published yet. Early access is coming soon.

Rights and limitations

VTI works on media you own or are authorised to use. It does not bypass platform protections and does not extract media you are not entitled to.

Automatic transcription and translation can contain errors. Review the output before publishing. Quality varies with audio clarity, accent, overlapping speech and subject-specific terminology.

Questions

Which file types can I upload?

Video in .mp4 or .mov, and audio in .mp3 or .wav. Check the signed-in upload screen for the current server size and duration limits.

Can I upload a recording of someone else's content?

Only if you own it or have permission to use it. VTI is for media you are entitled to process.

Do I get subtitles as well as a transcript?

Yes. Completed timestamped transcripts export as SRT or VTT in the original language. Speaker labels and translated exports depend on the configured providers and are not guaranteed.