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

# SoundClone - Create Audio Task

> Generate production audio using modelId from a completed preview task.

<Note>
  Use the `modelId` from a completed [preview task](/en/api-reference/sound-clone/clone-create). Poll [Query SoundClone Task](/en/api-reference/common/sound-clone-query) for the final `audioUrl`.

  `modelId` is valid for **3 days**. The first successful call to this endpoint within that window permanently activates the voice for future generation.

  Response envelope: `{ "code": 20000, "msg": "ok", "data": { ... } }`.
</Note>

## Request body

| Field            | Type    | Required | Description                                                                                                            |
| ---------------- | ------- | -------- | ---------------------------------------------------------------------------------------------------------------------- |
| `modelId`        | string  | Yes      | Voice model ID from preview query result.                                                                              |
| `contentText`    | string  | Yes      | Text to synthesize, max **10,000** characters. Insert `<#x#>` between words for pauses (`x` in seconds, `0.01–99.99`). |
| `soundVersion`   | string  | No       | `v1` or `v2`.                                                                                                          |
| `language`       | string  | No       | Language code, default `auto`.                                                                                         |
| `emotion`        | string  | No       | Default `neutral`. Values: `happy`, `sad`, `angry`, `fearful`, `disgusted`, `surprised`, `neutral`.                    |
| `speed`          | number  | No       | Speech rate `[0.5, 2]`, default `1.0`.                                                                                 |
| `vol`            | number  | No       | Volume `(0, 10]`, default `1.0`.                                                                                       |
| `pitch`          | integer | No       | Pitch `[-12, 12]`, default `0`.                                                                                        |
| `subtitleEnable` | boolean | No       | Generate subtitles, default `false`.                                                                                   |
| `subtitleType`   | string  | No       | When subtitles enabled, `word` for word-level; omit for sentence-level.                                                |

## Billing

Production audio has two fee components:

| Model config          | Description                                                            |
| --------------------- | ---------------------------------------------------------------------- |
| `sound-cloning-audio` | Character fee per **10,000 characters** from `contentText`             |
| `sound-cloning-voice` | **Voice fee**: charged on every production audio submission (per task) |

Character counting matches preview: Unicode runes, excluding `<#x#>` markers.

## Example

```bash theme={null}
curl --request POST \
  --url 'https://www.jimmyai.cn/api/open-api/v1/soundCloning/audios' \
  --header 'Authorization: Bearer sk_xxx' \
  --header 'Content-Type: application/json' \
  --data '{
    "modelId": "model_123456789",
    "contentText": "Welcome to voice cloning. This is production audio text.",
    "language": "Chinese",
    "soundVersion": "v1",
    "emotion": "neutral",
    "speed": 1.0,
    "vol": 1.0,
    "pitch": 0,
    "subtitleEnable": false
  }'
```

## Response example

```json theme={null}
{
  "code": 20000,
  "msg": "ok",
  "data": {
    "id": "audio_764fb3e7-8af2-4d2d-89a0-e58f8f3eb9c4",
    "object": "audio",
    "created": 1781777280,
    "model": "soundCloningAudio",
    "status": "queued",
    "error": null
  }
}
```


## OpenAPI

````yaml en/api-reference/openapi.json POST /api/open-api/v1/soundCloning/audios
openapi: 3.1.0
info:
  title: Jimmy AI OpenAPI
  description: API for Jimmy AI video generation services
  version: 1.0.0
servers:
  - url: https://www.jimmyai.cn
    description: Production server
security:
  - bearerAuth: []
paths:
  /api/open-api/v1/soundCloning/audios:
    post:
      summary: SoundClone - Create Audio Task
      description: Generate production audio using modelId from a completed preview task.
      operationId: createSoundCloneAudio
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/SoundCloneAudioRequest'
            examples:
              production:
                summary: Create production audio
                value:
                  modelId: model_123456789
                  contentText: Welcome to voice cloning. This is production audio text.
                  language: Chinese
                  soundVersion: v1
                  emotion: neutral
                  speed: 1
                  vol: 1
                  pitch: 0
                  subtitleEnable: false
      responses:
        '200':
          description: Task created
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/SoundCloneApiResponse'
              examples:
                queued:
                  summary: Created
                  value:
                    code: 20000
                    msg: ok
                    data:
                      id: audio_764fb3e7-8af2-4d2d-89a0-e58f8f3eb9c4
                      object: audio
                      created: 1781777280
                      model: soundCloningAudio
                      status: queued
                      error: null
components:
  schemas:
    SoundCloneAudioRequest:
      type: object
      required:
        - modelId
        - contentText
      properties:
        modelId:
          type: string
        contentText:
          type: string
          description: Text to synthesize, max 10000 characters
        soundVersion:
          type: string
          enum:
            - v1
            - v2
        language:
          type: string
          default: auto
        emotion:
          type: string
          enum:
            - happy
            - sad
            - angry
            - fearful
            - disgusted
            - surprised
            - neutral
          default: neutral
        speed:
          type: number
          minimum: 0.5
          maximum: 2
          default: 1
        vol:
          type: number
          exclusiveMinimum: 0
          maximum: 10
          default: 1
        pitch:
          type: integer
          minimum: -12
          maximum: 12
          default: 0
        subtitleEnable:
          type: boolean
          default: false
        subtitleType:
          type: string
          enum:
            - word
      example:
        modelId: model_123456789
        contentText: Welcome to voice cloning. This is production audio text.
        language: Chinese
        soundVersion: v1
        emotion: neutral
        speed: 1
        vol: 1
        pitch: 0
        subtitleEnable: false
    SoundCloneApiResponse:
      type: object
      properties:
        code:
          type: integer
          example: 20000
        msg:
          type: string
          example: ok
        data:
          $ref: '#/components/schemas/SoundCloneTaskData'
    SoundCloneTaskData:
      type: object
      properties:
        id:
          type: string
        object:
          type: string
          example: audio
        created:
          type: integer
          format: int64
        model:
          type: string
          enum:
            - soundCloningClone
            - soundCloningAudio
        status:
          type: string
          enum:
            - queued
            - processing
            - completed
            - failed
        error:
          type:
            - string
            - 'null'
      example:
        id: audio_16b635ba-5889-4fa5-bbcc-bf67a38c353a
        object: audio
        created: 1781777280
        model: soundCloningClone
        status: queued
        error: null
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer

````