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

# Create Re-translation

> Modify project script and create new translation

<Warning>
  Re-translation functionality is not available to all users by default. If you wish to use this feature, please contact us at [support@dubformer.ai](mailto:support@dubformer.ai).
</Warning>

<RequestExample>
  ```bash cURL theme={null}
  curl -X POST https://app.dubformer.ai/api/v1/projects/{project_id}/translations \
    -H "Authorization: Bearer YOUR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "target_script": [
        {
          "start_ms": 100,
          "end_ms": 1544,
          "text": "Au revoir le monde!",
          "speaker_id": 1
        }
      ],
      "target_speakers": [
        {
          "speaker_id": 1,
          "voice_key": "53f154:fr-FR-DeniseNeural",
          "style": "feminine"
        }
      ],
      "mixing_mode": "voiceover_only"
    }'
  ```

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

  url = 'https://app.dubformer.ai/api/v1/projects/{project_id}/translations'
  headers = {
      'Authorization': 'Bearer YOUR_API_KEY',
      'Content-Type': 'application/json',
  }
  data = {
      "target_script": [
          {
              "start_ms": 100,
              "end_ms": 1544,
              "text": "Au revoir le monde!",
              "speaker_id": 1
          }
      ],
      "target_speakers": [
          {
              "speaker_id": 1,
              "voice_key": "53f154:fr-FR-DeniseNeural",
              "style": "feminine"
          }
      ],
      "mixing_mode": "voiceover_only"
  }

  response = requests.post(url, headers=headers, json=data)
  print(response.json())
  ```

  ```javascript JavaScript theme={null}
  const url = 'https://app.dubformer.ai/api/v1/projects/{project_id}/translations';
  const headers = {
      'Authorization': 'Bearer YOUR_API_KEY',
      'Content-Type': 'application/json',
  };
  const data = {
      target_script: [
          {
              start_ms: 100,
              end_ms: 1544,
              text: "Au revoir le monde!",
              speaker_id: 1
          }
      ],
      target_speakers: [
          {
              speaker_id: 1,
              voice_key: "53f154:fr-FR-DeniseNeural",
              style: "feminine"
          }
      ],
      mixing_mode: "voiceover_only"
  };

  fetch(url, {
      method: 'POST',
      headers,
      body: JSON.stringify(data),
  })
  .then(response => response.json())
  .then(data => console.log(data));
  ```
</RequestExample>

## Path Parameters

<ParamField path="project_id" type="string" required>
  The unique identifier of the project to re-translate.
</ParamField>

## Request Body

<ParamField body="target_script" type="array" required>
  Array of target language script segments for dubbing.

  **Timing and Speaker Behavior:**

  * **Speaker assignments are required** - Each `speaker_id` must correspond to a speaker in `target_speakers`. If not specified, the request will be rejected with validation error
  * **Timings may be modified** - System adjusts timings to match synthesized speech length and avoid excessive speed changes, unless `use_fixed_timings: true` is set

  <Expandable title="Script Object Properties">
    <ParamField body="start_ms" type="number" required>
      Start time in milliseconds.
    </ParamField>

    <ParamField body="end_ms" type="number" required>
      End time in milliseconds.
    </ParamField>

    <ParamField body="text" type="string" required>
      Text of the translation to synthesize.
    </ParamField>

    <ParamField body="speaker_id" type="number" required>
      Speaker ID corresponding to target\_speakers.
    </ParamField>
  </Expandable>
</ParamField>

<ParamField body="target_speakers" type="array" required>
  Array of target speaker configurations for dubbing.

  <Expandable title="Speaker Object Properties">
    <ParamField body="speaker_id" type="number" required>
      Unique speaker identifier (must match script speaker\_id values).
    </ParamField>

    <ParamField body="style" type="string" required>
      Speaker style: `masculine` or `feminine`.
    </ParamField>

    <ParamField body="voice_key" type="string" required>
      Voice identifier. Can be:

      * `soundalike` for AI-generated voices matching original speakers
      * `emotional_transfer` for emotional soundalike voices
      * Specific voice key from [Get Voices](/platform/endpoints/get-voices)
    </ParamField>
  </Expandable>
</ParamField>

<ParamField body="mixing_mode" type="string" optional default="voiceover_with_original_track">
  Audio mixing mode:

  * `voiceover_only` - Only voiceover without the original track
  * `voiceover_with_original_track` - Voiceover with the original track
  * `voiceover_without_original_voice` - Smart vocal removal dubbing
</ParamField>

<ParamField body="use_fixed_timings" type="boolean" optional default="false">
  Whether to use fixed timings from the target script. By default, timings may be adjusted to fit the original video better.
</ParamField>

<ParamField body="tts_volume" type="string" optional default="normal">
  TTS volume level: `very_quiet`, `quieter`, `normal`, `louder`, `very_loud`.
</ParamField>

## Response

<ResponseField name="project_id" type="string">
  Unique identifier for the project.
</ResponseField>

<ResponseField name="cost_minutes" type="number">
  Number of minutes charged for this re-translation (typically 0).
</ResponseField>

<ResponseField name="estimated_completion_date" type="string">
  ISO timestamp of estimated completion time.
</ResponseField>

<ResponseField name="balance_minutes" type="number">
  Remaining balance in minutes.
</ResponseField>

<ResponseField name="translations_count" type="number">
  Total number of translations for this project.
</ResponseField>

<ResponseExample>
  ```json Success Response theme={null}
  {
    "project_id": "12345",
    "cost_minutes": 0,
    "estimated_completion_date": "2024-06-05T12:00:00Z",
    "balance_minutes": 90,
    "translations_count": 1
  }
  ```
</ResponseExample>

### Getting Original Script Data

Use [Get Project](/platform/endpoints/projects/get-project) to retrieve the original `output_source_script`, `output_target_script`, and `output_target_speakers` as starting points for your re-translation.

### Timing Considerations

* `start_ms` and `end_ms` should align with natural speech boundaries
* Large timing changes may affect lip-sync quality
* Use `use_fixed_timings: true` to prevent automatic timing adjustments

### Voice Selection

* Use specific voice keys from [Get Voices](/platform/endpoints/get-voices) for consistent results
* `soundalike` voices attempt to match original speaker characteristics
* `emotional_transfer` provides more expression but may be less stable