> ## Documentation Index
> Fetch the complete documentation index at: https://docs.snapgen.org/llms.txt
> Use this file to discover all available pages before exploring further.

# Voice isolation

> Remove background noise and music from a recording and receive the isolated voice as MP3.

`POST /v1/audio/isolation` removes background noise, music, and ambience from a recording and returns the isolated voice as an MP3 file in the response body. The recording must be at least 4.6 seconds long.

| Model | Input | Price |
| - | - | - |
| [`eleven-voice-isolator`](/api-manual/audio/eleven-voice-isolator) | 4.6 to 3,600 seconds, up to 50 MB | \$0.003 per second (\$0.18 per minute) |

<ParamField body="model" type="string" required>
  Set to `eleven-voice-isolator`.
</ParamField>

<ParamField body="file" type="file">
  The recording, in a multipart field named `file`, up to 50 MB. Send `file`
  or `audio_url`, not both.
</ParamField>

<ParamField body="audio_url" type="string">
  Public `http` or `https` URL of the recording. The gateway downloads it, up
  to 50 MB. Send `audio_url` or `file`, not both.
</ParamField>

This endpoint takes no other fields. In a multipart upload, send one `model`
field and one file in `file`. The gateway accepts WAV, AIFF, MP3, AAC, MP4,
M4A, MOV, FLAC, Ogg, and WebM files whose length can be read.

<Warning>
  The provider rejects recordings shorter than 4.6 seconds, so the gateway
  returns `audio_too_short` for them before any balance is reserved.
</Warning>

## Response

A successful request returns HTTP `200` with MP3 audio as the body
(`Content-Type: audio/mpeg`). The response carries `x-gateway-execution-id`.

## Billing

The gateway bills the measured length of the input at \$0.003 per second,
rounded up to whole seconds after a 0.1-second allowance. A 10-second clip
costs \$0.03; a one-hour recording costs \$10.80. Failed requests aren't
charged. This endpoint rejects `Idempotency-Key`; if a request times out, check
your Console request logs before you retry.

## Errors

| Status | `error.code` | Cause |
| - | - | - |
| 400 | `audio_input_required` | Neither `file` nor `audio_url` was sent. |
| 400 | `audio_too_short` | The recording is shorter than 4.6 seconds. |
| 400 | `audio_too_long` | The recording is longer than 3,600 seconds. |
| 400 | `invalid_request` | A field other than `audio_url` was sent, or both `file` and `audio_url` were sent. |
| 400 | `invalid_multipart` | The form has no `model` field, more than one file, a repeated field, or the file isn't in the `file` field. |
| 400 | `unsupported_audio_format` | The format isn't supported, or its length can't be read. |
| 400 | `audio_download_failed` | The gateway couldn't download `audio_url`. |
| 402 | `insufficient_funds` | Your balance can't cover the request. |
| 413 | `audio_too_large`, `request_too_large` | The downloaded file or the upload is larger than 50 MB. |

See [Errors](/errors) for rate limits and provider failures.

<RequestExample>
  ```bash Upload a file theme={null}
  curl https://api.snapgen.org/v1/audio/isolation \
    -H "Authorization: Bearer $SNAPGEN_API_KEY" \
    -F model=eleven-voice-isolator \
    -F file=@noisy-vlog.mp3 \
    --output voice.mp3
  ```

  ```bash Audio URL theme={null}
  curl https://api.snapgen.org/v1/audio/isolation \
    -H "Authorization: Bearer $SNAPGEN_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "eleven-voice-isolator",
      "audio_url": "https://example.com/noisy-vlog.mp3"
    }' \
    --output voice.mp3
  ```

  ```python Python theme={null}
  import os

  import requests

  with open("noisy-vlog.mp3", "rb") as audio:
      response = requests.post(
          "https://api.snapgen.org/v1/audio/isolation",
          headers={"Authorization": f"Bearer {os.environ['SNAPGEN_API_KEY']}"},
          data={"model": "eleven-voice-isolator"},
          files={"file": ("noisy-vlog.mp3", audio, "audio/mpeg")},
          timeout=600,
      )
  response.raise_for_status()
  with open("voice.mp3", "wb") as output:
      output.write(response.content)
  ```

  ```javascript Node.js theme={null}
  import { openAsBlob } from "node:fs";
  import { writeFile } from "node:fs/promises";

  const form = new FormData();
  form.append("model", "eleven-voice-isolator");
  form.append("file", await openAsBlob("noisy-vlog.mp3"), "noisy-vlog.mp3");

  const response = await fetch("https://api.snapgen.org/v1/audio/isolation", {
    method: "POST",
    headers: { Authorization: `Bearer ${process.env.SNAPGEN_API_KEY}` },
    body: form,
  });
  if (!response.ok) throw new Error(await response.text());
  await writeFile("voice.mp3", Buffer.from(await response.arrayBuffer()));
  ```
</RequestExample>

<ResponseExample>
  ```text 200 theme={null}
  HTTP/1.1 200 OK
  content-type: audio/mpeg
  cache-control: no-store
  x-gateway-execution-id: 5b1e9f3a-2c4d-4e6f-8a7b-9c0d1e2f3a4b

  <binary MP3 audio>
  ```

  ```json 400 theme={null}
  {
    "error": {
      "message": "The audio must be at least 4.6 seconds long",
      "type": "invalid_request_error",
      "param": null,
      "code": "audio_too_short"
    }
  }
  ```
</ResponseExample>