About Eleven Voice Changer
Eleven Voice Changer re-voices a speech recording in a different voice while keeping the original timing, emotion, and delivery.
The performance in the source clip drives the output, so whispers, laughs, pacing, and emphasis carry through to the new voice. It works across 29 languages and can strip background noise from the input before converting. It suits replacing scratch voiceover, giving one performer several characters, anonymizing speakers, and building paired speech datasets. Each clip can be up to 5 minutes long.
| Metric | Value |
|---|---|
| Max Input | 5 minutes |
| Multilingual | Yes, 29 languages |
Ready to build with Eleven Voice Changer?
Try Eleven Voice Changer in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "elevenlabs-voice-changer",
"messages": [
{
"role": "user",
"content": "Try sending a message."
}
]
}'Request parameters
Every field Eleven Voice Changer accepts in the request body. See the API reference for response formats.
https://hub.oxen.ai/api/ai/chat/completions| Field | Type | Required | Default | Description |
|---|---|---|---|---|
input_audio | stringuri | Yes | — | Speech recording to re-voice, up to 5 minutes. Its timing, emotion, and delivery carry over. |
voice_id | string | Yes | "EXAVITQu4vr4xnSDxMaL" | The voice to convert the recording into.pNInz6obpgDQGcFmaJgBXb7hH8MSUJpSbSDYk0k2hpp4J3VqNfWAUOO0d1UspqHfZKP75CvOlQylNhV4nPczCjzI2devNBz1zQrbN2lVS1w4EtoT3dr4eOWOIKne3meq5aSn9XLyUdCDiP95p4xoKVk53GoZ742BonwK4e9ZLuTAKqWW03F9cjVigY5qzO86Huf0OWalJBFqnCBsd6RMkjVDRZzbSOYHLrjzK2X1ezoPC6crcgSgspJ2msm6clMCkdW9FGY2WhTYpPnrIDTdsKH5TX3LPaxmHKxFdv7VOQHJpFZP5JQG7iQjIQuC4BkuXrExE9yKIg1WjnnlVkGXSAz9YHcvj6GT2YYXdXwwCwhRBWXzGAHq8TQ4Fs17EXAVITQu4vr4xnSDxMaLbIHbv24MWmeRgasZH58o |
remove_background_noise | boolean | No | false | Isolate the speech from background noise before converting it. |
stability | number | No | 0.5 | Lower values give more varied delivery; higher values stay closer to a fixed baseline. Range: 0 – 1 |
similarity_boost | number | No | 0.75 | How closely the output follows the target voice. Range: 0 – 1 |
seed | integernullable | No | — | Optional seed for best-effort deterministic output. Range: 0 – 4294967295 |