> ## 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.

# Train Model

> Train a custom AI voice model after [creating it](/api-reference/models/create) in a pending state.

### Request

<ParamField path="model_id" type="string" required>
  The model ID to train. This is the ID of the model you created in a pending state.
</ParamField>

<ParamField body="epochs" type="integer" required>
  The number of epochs to train the model. The minimum value is 100. The allowed range is 1 to 100,000. More epochs will result in a better model, but will take longer to train.
</ParamField>

### Response

<ResponseField name="status" type="string">
  The status of the training task. Possible values are: <code>training</code>, <code>completed</code>, <code>failed</code>.
</ResponseField>

<ResponseField name="model_id" type="string">
  The ID of the model being trained. This is the same as the `model_id` in the request URL.
</ResponseField>

<ResponseField name="current_epoch" type="integer">
  The current epoch of the training task. This value will be 0 if the training task has not started yet.
</ResponseField>

<RequestExample>
  ```bash Example Request theme={null}
  curl --location --request POST 'https://api.revocalize.ai/models/123456/train' \
  --header 'Content-Type: application/json' \
  --header 'Authorization: Bearer <token>' \
  --form 'epochs=100'
  ```
</RequestExample>

<ResponseExample>
  ```json Response theme={null}
  {
    "status": "training",
    "model_id": "123456",
    "current_epoch": 50001,
  }
  ```
</ResponseExample>