MP3 · WAV · M4A · record in the browser · free plan
Audio Translator — translate audio voice to voice, 33 languages
Upload a voice note, podcast or lecture — or record one — and get it back spoken in another language, in the speaker's own voice. 33 target languages, auto-detected source, free plan.
- Speech in, speech out
- 33 languages
- Keeps the voice
- Record or upload
Updated by the Kenerate AI team
Made with Kenerate
On this page
Quick answer
What is an audio translator?
An audio translator turns speech in one language into speech in another. On Kenerate AI you upload an audio file up to 50 MB, or record in the browser, pick one of 33 languages, English included, and the ElevenLabs dubbing engine returns it spoken in the speaker's voice, with the source language auto-detected. It works on the free plan.
Key facts
- Target languages
- 33
- Audio files
- Up to 50 MB
- Longest audio
- 15 min
- Free plan
- Yes
- Formats
- MP3, WAV, M4A, AAC, OGG, FLAC, Opus
- Source languages
- 57, auto-detected
- Speakers
- Up to 32
- Output
- Translated speech, not a transcript
Real demo
An English lecture in Spanish and Chinese
Turn the sound on and switch languages. Same speaker, same voice, new language.
- English (original). A Wan 3 clip with an English line.
- Spanish. Auto-detected English, dubbed to Spanish.
- Chinese. The same clip, dubbed to Chinese.
Shown on video so you can hear it; audio files work the same way.
Translate your audioReal results
Speech you might translate
Real 5-second Wan 3 clips with speech — lectures, calls, interviews, tours and voice notes.
How to
How to translate audio
- Time needed
- Steps
- 4 steps
Step 1
Open AI dubbing and choose audio
Sign in — it works on the free plan.
Step 2
Upload or record
MP3, WAV, M4A, AAC, OGG, FLAC, Opus or WebM, up to 50 MB and 15 minutes — or record in the browser.
Step 3
Pick the language
33 targets; the source is auto-detected.
Step 4
Download
The translated speech, in the speaker's voice.
See it in the app
Open AI Dubbing and upload a video or an audio file, or pick a clip from your history.
Watch the tour · 2:03
Video or audio, 33 languages, speakers & background, side-by-side compare, two voices, your dubs & chat
Chapters
Engines
Tools for translating speech
Audio, video and captions — the same languages across the studio.
- Free plan
ElevenLabs
Translate audio
- Input
- Audio file or recording, up to 15 min
- Output
- Speech in 33 languages
Open Translate audioBest for
Voice notes, podcasts, lectures
- Free plan
ElevenLabs
Video dubbing
- Input
- Video up to 15 min / 500 MB
- Output
- Dubbed video
Open Video dubbingBest for
YouTube, courses, ads
ElevenLabs, MiniMax, Qwen
Voice Studio
- Input
- Text
- Output
- Speech in up to 40 languages
Open Voice StudioBest for
Reading a written translation aloud
VEED
Subtitles
- Input
- Video up to 4 min
- Output
- Captions in the spoken language
Open SubtitlesBest for
Reading along
The demo above ran on Kenerate's dubbing tool (ElevenLabs).
Tips
Clean translations
What makes the result sound right.
Record close to the mic in a quiet room.
One speaker at a time translates best.
Set the speaker count for interviews.
Drop background music if it muddies the voice.
Keep sentences short for natural phrasing.
Check names and numbers in the result.
Example uses
How creators use Translate audio
Illustrative examples of typical workflows, not customer reviews.
Lecturer
A lecturer can upload a recorded class and share it in another language in their own voice.
Podcaster
A podcaster can translate an episode into several of the 33 languages to reach new listeners.
Traveller
A traveller can record a voice note in the browser and send it to a host family in their language.
FAQ
Translate Audio questions
12 questions
How do I translate audio?
Upload the file (or record it), pick one of 33 languages, and download the translated speech — the source language is auto-detected.
Link to this answerCan it keep my own voice?
Yes — the ElevenLabs dubbing engine re-voices each speaker with a clone of their voice.
Link to this answerIs there a Spanish voice translator?
Yes — translate any audio into Spanish, or Spanish audio into any of the other 32 languages.
Link to this answerCan I translate Chinese audio to English?
Yes — Chinese is auto-detected as a source and English is a target, and the reverse works too (see the demo).
Link to this answerWhat file types are supported?
MP3, WAV, M4A, AAC, OGG, FLAC, Opus and WebM audio, up to 50 MB and 15 minutes — or record in the browser.
Link to this answerIs this different from Google Translate conversation mode?
Google's conversation mode speaks translations aloud in a live chat. This tool translates a recording and gives you the file, in the speaker's own voice.
Link to this answerCan I translate audio for free?
Yes, to start: translating audio works on the free plan with the sign-up credits, so you can try a voice note or a short recording. Longer audio, up to 15 minutes, uses one-time credit packs that never expire.
Link to this answerHow do I translate audio to English?
Upload the file or record it, leave the source on auto-detect, pick English as the target and download the result. It works from any of the 57 source languages, including the ones with their own guide below, like Spanish, French, Japanese, Korean, Portuguese and Arabic.
Link to this answerWhich languages does the audio translator support?
It speaks 33 target languages and listens to 57 source languages. 25 of those, such as Thai, Urdu, Persian, Hebrew and Swahili, work as a source only, so you can translate them into English but not the other way round. The full list is further down this page.
Link to this answerCan I use it as an MP3 translator?
Yes. Upload an MP3 up to 50 MB and 15 minutes long, and it comes back as translated speech. WAV, M4A, AAC, OGG, FLAC, Opus and WebM audio work the same way.
Link to this answerDoes it translate audio to text?
No. This tool returns speech, not a transcript. If you need the words on screen, the Subtitles tool adds captions to a video in the language spoken in it.
Link to this answerCan it translate a recording with several speakers?
Yes. It handles up to 32 speakers, and you can set the speaker count for interviews and panels. One speaker at a time still translates best, so check names and numbers in the result.
Link to this answerIn depth
Translate Audio, explained
On this page
How speech-to-speech translation works
The classic pipeline is three steps: speech recognition, text translation, then text-to-speech. Meta's SeamlessM4T replaces that chain with one model covering about 100 input languages. Voice-preserving tools add a clone of the speaker so the translation still sounds like them.
Which languages the audio translator supports
It can speak the 33 languages in the first three groups below. Tagalog and Filipino are listed separately in the tool.
- Most used: English, Hindi, Spanish, French, German, Japanese, Korean, Chinese, Portuguese, Arabic, Tamil, Indonesian.
- More of Europe: Italian, Russian, Dutch, Polish, Ukrainian, Swedish, Norwegian, Danish, Finnish, Greek, Czech, Slovak, Hungarian, Romanian, Bulgarian, Croatian.
- More of Asia and the Middle East: Malay, Filipino, Tagalog, Vietnamese, Turkish.
- Source only, so you can translate from them but not into them: Afrikaans, Armenian, Azerbaijani, Belarusian, Bosnian, Catalan, Estonian, Galician, Hebrew, Icelandic, Kannada, Kazakh, Latvian, Lithuanian, Macedonian, Maori, Marathi, Nepali, Persian, Serbian, Slovenian, Swahili, Thai, Urdu, Welsh.
When to use which
Live conversation with someone in front of you: a phone app's conversation mode. A recording you want to share — a podcast, lecture or voice note — in another language: translate the file and keep the voice.
Explore
Every Kenerate video tool
Generators, tools, models and guides — all in one studio.
By the Kenerate AI teamLast updated and reviewed
Sources: Kenerate video studio · Meta AI — SeamlessM4T · Google Translate Help — conversations · ElevenLabs — Dubbing docs
