Transcribe · Translate · Voice

Translate a video into another language, voiced on its own timing

Upload the video, get the transcript, translate it into one of 18 languages and voice it in a natural voice. Every line is placed at the second it was said, so the track lines up with the picture: one MP3 as long as the video, ready to go under it. Two people talking? Each can have a voice of their own.

Translate a video →
15 free minutes at sign-up · pay per use · credits never expire · no subscription.

From a video to a voice-over in another language

The sound is taken out of the video in your browser; the video itself is never uploaded.

product-tour-es.mp3
8:40 video · English → Spanish · Enhanced
Voice track
1Upload the video in Transcribe. Your browser takes the sound out of the MP4, MOV or WebM and only that is uploaded. The transcript comes back in a few minutes, in any of 99 languages.
2Translate it. Pick one of 18 languages. Read the translation and fix what you would say differently: what you see here is what the voice will read.
3Voice it on the original timing. In the Voice menu choose "Voice on the original timing". Each line is voiced in the voice you pick and placed where it was said; several people get a voice each. The price is on the button before anything is charged.
4Put the track on the video. Download the MP3 and drop it onto the video in our free tool, which runs in the browser, or in your editor, or add it in YouTube Studio as an audio track in another language.
What you get
  • product-tour-es.mp3 (one track as long as the video)
  • Each line as its own MP3 (ZIP)
  • The translated subtitles (SRT, VTT)
  • product-tour-es.mp4 (from the free tool)

Who translates videos this way

Videos where a voice explains what the picture shows, rather than people talking to the camera.

Product demos and tutorials

A screen recording narrated once, in one language.

Now: the same narration in Spanish, German or Japanese, on the same timing, without a new recording.

Online courses

Lectures and lessons that only one language group can follow.

Now: a voiced version for each market, each lesson's track as long as the lesson.

YouTube channels

Viewers abroad get subtitles at best.

Now: a voiced track in their language, added in YouTube Studio as another audio track.

Training and onboarding

Staff in other countries watch videos they half understand.

Now: the training in their language, voiced and checked line by line before it goes out.

Explainers and presentations

A slide deck recorded with a voice-over in English only.

Now: the deck's video with the voice-over in the audience's language.

Documentaries and interviews with narration

Narration that needs a translator, a voice actor and a studio.

Now: a draft voice-over in an afternoon, every line editable before the final cut.

A video translation at a glance

What a video translation costs

Three steps, each priced on its own, all from one balance. The voice price is on the button before anything is charged.

Transcribe10 credits a minute of video. An hour of video is 600 credits; the first 15 minutes at sign-up are free.
TranslateThe first two translations of a transcript are free. A third language and more cost 1 credit per 1,500 characters.
Voice50 credits per 1,000 characters on Standard, 110 on Enhanced, 160 on Premium. Steady narration runs to about 900 characters a minute, so a 10-minute video is about 1,000 credits on Enhanced.
An hourAbout 3,300 credits on Standard, 6,500 on Enhanced, 9,200 on Premium. Transcription and voice together for an hour of steady narration; videos with pauses cost less to voice.

Packs: $5 = 2,400 credits, $10 = 6,000, $25 = 16,800, $50 = 36,000. Credits never expire, there is no subscription, and there is a 14-day refund. All prices on the pricing page →

Frequently asked questions

Not covered here? Ask us, we usually reply within a business day.

How do I translate a video into another language with a voice?

Upload the video in Speecho's Transcribe tab, translate the transcript, then choose "Voice on the original timing" in the translation's Voice menu. You get one MP3 as long as the video, each line placed where it was said; put it on the video in the free tool or in your editor.

Will the voice match the speaker's lips?

No. The lines start at the same seconds as the original speech, but nothing changes the picture. It suits videos where a voice explains what is on screen: tutorials, screen recordings, courses, presentations, narration. For close-ups of someone talking, the mouth will not match.

What if the translation is longer than the original?

A line that runs over its time is sped up by up to 25%, the voice keeping its pitch. If that is not enough, the next lines start a little late until a pause takes the delay up. Before voicing, the panel names the lines likely to run over, so you can shorten them; afterwards the card shows which were sped up or late.

Can a video with two or more people get several voices?

Yes. When the transcript tells the people apart, each gets a voice of their own, up to eight. Who says each line comes from speech recognition and can be wrong, so check it before voicing; a line in the wrong voice can be moved to another voice and voiced again on its own.

Is my video uploaded?

Only its sound. When you add a video in Transcribe, your browser takes the audio out of it and uploads that. The free tool that puts the new track on the video also runs in your browser. The video file stays on your computer.

What happens to the music and sound effects?

The voice track holds only the new voice. In the free tool you can keep the original sound quietly underneath, music and effects included; the original speech stays in it too, so this suits videos with little talking. Otherwise add the music again in your editor.

Can I put the translation on YouTube as another language?

Yes. Where your channel can add audio tracks in YouTube Studio, upload the MP3 as the track of the new language: it is as long as the video and starts where the video starts, so nothing needs lining up. Add the translated subtitles from the same transcript as well.

Can I fix a line after voicing?

Yes. Open the voiced set in your history, correct the line's text or give it another voice, and voice it again: only that line is charged, at its own characters, and the track is put together again by itself.

How long can the video be?

Up to 2 hours for the voice-over for now. Transcription takes longer recordings; voice a longer video in parts.

Which languages are there?

Transcription understands 99 languages and translation goes into 18. The voices speak many languages and accents, with native voices for the main ones and universal voices for the rest.

Other ways to work with video

Your video, in another language.

Upload it, translate it, voice it on its own timing, put the track back. A 10-minute video comes to about 1,100 credits on Enhanced.

Translate a video →