Official BytePlus partnerBytePlus, a ByteDance company
AI voice translator
AI voice translator: translate a voice clip
Upload or record a voice clip, choose a target language and get the transcript, the translated text and the translation read aloud by a built-in voice. 11 source languages plus auto-detect, 11 target languages.
- 11 source languages
- 11 target languages
- Transcript, translation and audio
- 3 credits per minute
Last updated
How it works
- 1
Add a clip
Upload an audio file of up to 50 MB or record one in the browser.
- 2
Choose the languages
Leave the source on auto-detect or pick it, then choose the language to translate into.
- 3
Get three results
The original transcript, the translated text and the translation spoken by a built-in voice, ready to play and download.
Languages
From (or auto-detect)
- English
- Mandarin
- Japanese
- Spanish
- Portuguese
- French
- German
- Korean
- Italian
- Russian
- Arabic
Into
- English
- Mandarin
- Japanese
- Spanish
- Portuguese
- French
- German
- Korean
- Italian
- Russian
- Arabic
Good to know
- It translates a finished recording, not a live call or stream.
- The translation is spoken by a built-in voice for the target language, not by the original speaker.
- Clear speech from one speaker gives the best transcript and translation.
- Only need the text? Speech to Text costs 1 credit per 5 minutes of audio.
Pricing
A clip costs 3 credits per started minute of audio, shown before you start. Failed jobs are refunded automatically.
Voice translator questions
Which languages can it translate?
From English, Mandarin, Japanese, Spanish, Portuguese, French, German, Korean, Italian, Russian, Arabic (or auto-detect) into English, Mandarin, Japanese, Spanish, Portuguese, French, German, Korean, Italian, Russian, Arabic.
Does it translate during a live call?
No. It works on a recorded or uploaded clip: you add the clip, it returns the transcript, the translation and a spoken version.
Does the translation keep my voice?
No. The translation is read by a built-in voice for the target language.
How much does it cost?
3 credits per started minute of audio, for clips of up to 50 MB. Failed jobs are refunded.
Can I just get a transcript?
Yes. Speech to Text transcribes a clip in 8 languages, or with auto-detect, for 1 credit per 5 minutes of audio.
Which platform does the audio studio run on?
Built on BytePlus, a ByteDance company. KreatorFlow is an official partner of BytePlus, a ByteDance company; the audio studio and its credit prices are KreatorFlow's own.
Translate your first clip
Upload a voice clip and get it back in one of 11 languages, as text and speech.
Keep exploring
- AI voice generator
- AI text to speech
- AI voice cloning
- Multilingual text to speech
- AI voiceover generator
- AI podcast voices
- AI audiobook narrator
- Add a voiceover to an AI video
- Clone your voice safely
- Timestamped audio prompts
- Two-speaker AI dialogue
- AI audio studio
- Add a voiceover to an AI video
- Seedance 2.0 video generator (native audio)
- Seedance 2.5 video generator (native audio)
- Guides
- Acceptable Use Policy