Same words, two languages, one timeline.
A 26-second English clip we recorded ourselves, run through the real pipeline: transcribe, translate, voice, assemble. This one uses a standard Mandarin voice; your file can use your own. Click any line to play from there.
Translation shown exactly as produced, no human polish · timecodes from the English transcript
How to translate an audio file, in three steps.
No studio and no re-recording. You upload the original file and spend a few minutes reading the translation.
- 1
Upload your audio
MP3, M4A, WAV, AAC, FLAC or OGG, up to 120 minutes. Pick the spoken language and the one you want, and confirm rights and consent.
IN · MP3 / M4A / WAV · ≤ 95 MB - 2
Check the translation
We transcribe with Whisper and translate in context, flagging any number or date that didn't survive. Fix any sentence before a single second of audio is generated.
EDIT · sentence by sentence · autosave - 3
Listen and download
Your translation is voiced — in your cloned voice or a standard one — laid on the original timeline, loudness-matched and exported as an MP3 labelled AI-generated.
OUT · MP3 + bilingual transcript
Built for people who publish their own voice.
Most tools give you a transcript in another language, or a stranger's voice reading it. This is for when the recording is yours and you want it to stay yours.
With your consent, the dub uses a clone of your own voice, not a stock narrator. About own-voice dubbing
The translation waits for you. Edit a line, and only that line is re-voiced.
Every figure in the source must appear in the translation; misses are flagged before voicing.
Each sentence starts where it started in the original, so pauses and breathing room survive.
Source and translation side by side with timecodes — click a line to hear it.
Audio only: we replace the soundtrack, we don't edit video or lip movements.
Six languages, any direction.
English, Spanish, German, French, Japanese and Mandarin Chinese — as source or target, in any combination.
Pay per finished minute. Try 10 minutes free.
Edits only re-voice the sentences you changed, so corrections don't cost twice. See full pricing.
Q.01How do I translate an audio file?
Upload the file above, pick the language spoken in it and the language you want, tick the three consent boxes and press Start translating. We transcribe it, translate it, show you the translation to correct, then generate the new audio track. A 10-minute file usually takes a few minutes.
Q.02Can I translate an audio file to English?
Yes. Choose Spanish, German, French, Japanese or Chinese as the source and English as the target. See translate audio to English for tips.
Q.03Will the translated audio really sound like me?
If you choose Keep my own voice, we clone your voice from a clean 10–60 second stretch of your own recording and use it to read the translation. It is close, not perfect: accents and some expressiveness shift in another language. You can always switch to a standard voice instead.
Q.04Do you translate video or do lip-sync?
No. We only replace the audio track: you get a translated MP3. If you have a video, export its audio, translate it here, and put the new track back in your editor. We do not change mouths or faces.
Q.05Can I upload someone else's podcast or audio?
Only if you own the rights or have written permission, and only clone a voice that is yours or that you have explicit consent to use. Every upload records your confirmation.
Q.06How long do you keep my files?
Uploads, transcripts and dubs are deleted automatically 7 days after upload, and you can delete a job instantly from its page. Your audio is never used to train models. Details in our privacy policy.
Your next episode, in another language — still in your voice.
Translate an audio file