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

# Create Model

> This endpoint creates a new AI voice model. The model is created in a pending state. You must [train the model](/api-reference/training/train) before it can be used for synthesis.

### Request

<ParamField body="training_audio_files" type=".zip file" required>
  A zip file containing the training audio files. The zip file must contain the following files:

  <ol>
    <li>`model.json` - a JSON file containing the model metadata.</li>
    <li>`audio` - a folder containing the audio files.</li>
  </ol>
</ParamField>

### Response

<ResponseField name="model_id" type="string">
  The ID of the pending model. After training the model, this ID can be used to reference the model in other API calls.
</ResponseField>

<RequestExample>
  ```bash Example Request theme={null}
  curl --location --request POST 'https://api.revocalize.ai/models/create' \
  --header 'Content-Type: multipart/form-data' \
  --header 'Authorization: Bearer <token>' \
  --form 'training_audio_files=@"/path/to/training_audio_files.zip"'
  ```
</RequestExample>

<ResponseExample>
  ```json Response theme={null}
  {
    "model_id": "5f7b1b1b-1b1b-1b1b-1b1b-1b1b1b1b1b1b"
  }
  ```
</ResponseExample>