About Eleven Voice Isolator
Eleven Voice Isolator extracts clean speech from a recording, removing background noise, music, reverb, and ambient sound.
It keeps the speaker's voice and delivery intact while stripping everything around it, which makes it useful for cleaning up field and phone recordings, preparing voiceover, rescuing interview audio, and cleaning speech before transcription or voice cloning.
| Metric | Value |
|---|---|
| Min Input | 4.6 seconds |
Ready to build with Eleven Voice Isolator?
Try Eleven Voice Isolator 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-isolator",
"messages": [
{
"role": "user",
"content": "Try sending a message."
}
]
}'Request parameters
Every field Eleven Voice Isolator accepts in the request body. See the API reference for response formats.
POST
https://hub.oxen.ai/api/ai/chat/completions| Field | Type | Required | Default | Description |
|---|---|---|---|---|
input_audio | stringuri | Yes | — | Recording to clean up, between 4.6 seconds and 1 hour long. |