curl -X POST 'https://api.elevenlabs.io/v1/audio-isolation/stream' \
  -H "xi-api-key: $ELEVENLABS_API_KEY" \
  -F 'audio=@sample.bin' \
  -F 'file_format=other'

# POST /v1/audio-isolation/stream (ElevenLabs API)
Base URL: https://api.elevenlabs.io
Auth: xi-api-key: <ELEVENLABS_API_KEY>
Last verified: 2026-09-03

> Audio Isolation Stream

## Critical Gotchas
* Authentication uses the non-standard `xi-api-key` header, not `Authorization: Bearer`. Sending a Bearer token returns HTTP 401.
* Text-to-speech responses are raw binary audio, not JSON. Write the body to a file (`--output speech.mp3`) rather than parsing it.

## cURL
curl -X POST 'https://api.elevenlabs.io/v1/audio-isolation/stream' \
  -H "xi-api-key: $ELEVENLABS_API_KEY" \
  -F 'audio=@sample.bin' \
  -F 'file_format=other'

## Parameters
| Name | In | Type | Required | Description |
| :--- | :--- | :--- | :--- | :--- |
| audio | body | string | Yes | The audio file from which vocals/speech will be isolated... |
| file_format | body | string | No | The format of input audio. Options are 'pcm_s16le_16' or... |

## Response (200 OK)
"binary"

---
Need an API key? Get one at https://elevenlabs.io/app/sign-up

POST

/v1/audio-isolation/stream

ElevenLabs API

Audio Isolation Stream

Base URL: https://api.elevenlabs.io
Auth: xi-api-key: <ELEVENLABS_API_KEY>
Last verified: 2026-09-03 · upstream hash matched

Actions

Agents: curl -H "Accept: text/markdown" this URL
→ 197 tokens · Vary: Accept

Critical gotchas

Authentication uses the non-standard xi-api-key header, not Authorization: Bearer. Sending a Bearer token returns HTTP 401.

Text-to-speech responses are raw binary audio, not JSON. Write the body to a file (--output speech.mp3) rather than parsing it.

cURL

curl -X POST 'https://api.elevenlabs.io/v1/audio-isolation/stream' \  -H "xi-api-key: $ELEVENLABS_API_KEY" \  -F 'audio=@sample.bin' \  -F 'file_format=other'

Get a free ElevenLabs API key → sponsored

Parameters

Name	In	Type	Required	Description
audio	body	string	Yes	The audio file from which vocals/speech will be isolated from.
file_format	body	string	No	The format of input audio. Options are 'pcm_s16le_16' or 'other' For `pcm_s16le_16`, the input audio must be 16-bit PCM at a 16kHz sample rate, single channel (mono), and little-endian byte order. Latency will be lower than with passing an encoded waveform.

Response 200 OK

"binary"