# Play a cloned voice sample (/docs/api-reference/voice-cloning/getClonedVoiceSample)

> Stream the generated mp3 sample of a cloned voice. Only the owner can fetch it. 404 (sample_not_ready) when no sample exists yet. The request needs your API key in the Authorization header.

**GET** `/voices/{voice_id}/sample`

Stream the generated mp3 sample of a cloned voice. Only the owner can
fetch it. `404` (`sample_not_ready`) when no sample exists yet. The
request needs your API key in the `Authorization` header.

```yaml
operationId: getClonedVoiceSample
parameters:
  - in: path
    name: voice_id
    required: true
    schema:
      type: integer
    description: Id of the cloned voice.
responses:
  '200':
    description: The sample audio.
    content:
      audio/mpeg:
        schema:
          type: string
          format: binary
  '403':
    description: Voice cloning is not enabled for this account.
    content:
      application/json:
        schema:
          type: object
          properties:
            error:
              type: string
              description: Machine-readable error code.
            error_description:
              type: string
              description: Human-readable explanation.
            code:
              type: string
              description: |
                Stable, specific reason. Present on the newer endpoints (Voice
                cloning, WhatsApp); older endpoints return only `error`.
            request_id:
              type: string
              description: |
                Correlates this response with the server log. Present alongside
                `code`. Also sent as the `X-Request-Id` header.
  '404':
    description: No such voice, it belongs to another account, or no sample exists yet.
    content:
      application/json:
        schema:
          type: object
          properties:
            error:
              type: string
              description: Machine-readable error code.
            error_description:
              type: string
              description: Human-readable explanation.
            code:
              type: string
              description: |
                Stable, specific reason. Present on the newer endpoints (Voice
                cloning, WhatsApp); older endpoints return only `error`.
            request_id:
              type: string
              description: |
                Correlates this response with the server log. Present alongside
                `code`. Also sent as the `X-Request-Id` header.
        example:
          error: not_found
          error_description: Sample audio is not available yet.
          code: sample_not_ready
          request_id: req_2e9b6d1a8f43
  '502':
    description: The stored sample is unreadable. Regenerate it with `POST /voices/{voice_id}/sample`.
    content:
      application/json:
        schema:
          type: object
          properties:
            error:
              type: string
              description: Machine-readable error code.
            error_description:
              type: string
              description: Human-readable explanation.
            code:
              type: string
              description: |
                Stable, specific reason. Present on the newer endpoints (Voice
                cloning, WhatsApp); older endpoints return only `error`.
            request_id:
              type: string
              description: |
                Correlates this response with the server log. Present alongside
                `code`. Also sent as the `X-Request-Id` header.
        example:
          error: server_error
          error_description: The sample audio is unavailable. Try regenerating it.
          code: sample_unavailable
          request_id: req_5f0a3c7e2d81
```

**curl**

```bash
curl -X GET "https://omnidim.io/api/v1/voices/{voice_id}/sample" \
  -H "Authorization: Bearer $OMNIDIM_API_KEY"
```