Mira AI
Eleven Voice Changer — a new voice, the same performance
ElevenLabsVoice29 languagesRecord the line yourself, then give it another voice: Eleven Voice Changer keeps your timing, pauses and emotion and replaces only the timbre. It works on clips and audio files up to 2 min, in 29 languages.
ElevenLabs: expressive speech in 70+ languages, dialogue, music written to your cut, sound effects, dubbing and captions — the sound layer for every clip.
Open your galleryUse it through MCP
Voice change runs on a clip or audio file you already have: open it in your gallery and pick the voice change action.
What it does
- Your performance, another voiceTiming, intonation, breaths and laughs stay. Only the timbre changes, to the voice you pick.
- Video in, video outChange the voice in a clip and get the clip back with the new voice. Audio files come back as audio.
- Noise removalSwitch on noise removal to clean up a phone recording before the voice is changed.
- Library or your own voicesChoose any library voice, or one you designed and saved to your account.
Specification
- Provider
- ElevenLabs
- Provider model
eleven_multilingual_sts_v2- Languages
- 29 languages
- Limits on Mira
- source up to 2 min
- Output
- mp3, mp4
- Where it works
- Gallery: an action on your clip or audio fileMCP tools:
change_voicelist_voicesMira for Adobe panel (After Effects, Premiere Pro)
Cost in credits
2 credits per second
Billed by the second and rounded up to a whole credit.
| Example | Credits |
|---|---|
| 30 s of source audio | 60 |
| 2 min of source audio | 240 |
The composer always shows the current price before you generate.
Questions about Eleven Voice Changer
How long can the source be?
Up to 2 min of audio per run.
Does it translate the speech?
No. It keeps the language and the words. To change the language, use Eleven Dubbing.
Will the lips still match?
Yes. The timing of the original performance is kept, so the new voice lines up with the lips in the clip.
How much does it cost?
2 credits per second of source audio. The table above has worked examples.
Can I use it through MCP?
Yes: change_voice takes a generation or an uploaded file and a voice id from list_voices.