> ## 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 Project

> Create a new dubbing project

<RequestExample>
  ```bash cURL theme={null}
  curl -X POST https://app.dubformer.ai/api/v1/projects \
    -H "Authorization: Bearer YOUR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "name": "My Project",
      "source_lang": "en",
      "target_lang": "fr-FR",
      "source_video_url": "https://example.com/video.mp4",
      "use_soundalike_voices": true,
      "mixing_mode": "voiceover_with_original_track"
    }'
  ```

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

  url = 'https://app.dubformer.ai/api/v1/projects'
  headers = {
      'Authorization': 'Bearer YOUR_API_KEY',
      'Content-Type': 'application/json',
  }
  data = {
      "name": "My Project",
      "source_lang": "en", 
      "target_lang": "fr-FR",
      "source_video_url": "https://example.com/video.mp4",
      "use_soundalike_voices": True,
      "mixing_mode": "voiceover_with_original_track"
  }

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

  ```javascript JavaScript theme={null}
  const url = 'https://app.dubformer.ai/api/v1/projects';
  const headers = {
      'Authorization': 'Bearer YOUR_API_KEY',
      'Content-Type': 'application/json',
  };
  const data = {
      name: "My Project",
      source_lang: "en",
      target_lang: "fr-FR", 
      source_video_url: "https://example.com/video.mp4",
      use_soundalike_voices: true,
      mixing_mode: "voiceover_with_original_track"
  };

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

## Request Body

<ParamField body="name" type="string" optional>
  The name of the project for organization purposes.
</ParamField>

<ParamField body="source_lang" type="string" required>
  The source language of the video without locale (e.g., "en", "es", "fr").
  Get the full list from [Get Options](/platform/endpoints/get-options).
</ParamField>

<ParamField body="target_lang" type="string" required>
  The target language for dubbing with locale (e.g., "en-US", "fr-FR", "es-ES").
  Get the full list from [Get Options](/platform/endpoints/get-options).
</ParamField>

<ParamField body="source_video_url" type="string" required>
  Direct link to the source video file or YouTube URL.
</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_emotional_transfer" type="boolean" optional default="false">
  Enable emotional but less stable soundalike voices.
  <Note>Supports only English, Spanish, French, German, Italian, and Portuguese target languages.</Note>
</ParamField>

<ParamField body="use_soundalike_voices" type="boolean" optional default="false">
  Enable soundalike voices that match original speaker characteristics.
  <Note>Requires an [active subscription](https://app.dubformer.ai/subscriptions).</Note>
</ParamField>

<ParamField body="source_script_content" type="string" optional>
  Custom transcription of the source video in SRT, VTT, or plain text format.
  <Note>[Pro subscription](https://app.dubformer.ai/subscriptions) feature.</Note>

  **Timing and Speaker Behavior:**

  * **Timings are NOT preserved** - Original timings are ignored and recalculated based on speech boundaries in audio for precise alignment
  * **Speaker markup is NOT preserved** - Speaker tags (e.g., `<v Speaker1>`, `<v John>`) are ignored and not extracted as speaker information
</ParamField>

<ParamField body="source_script" type="array" optional>
  Structured source script with precise timings. Array of objects with `start_ms`, `end_ms`, and `text` fields.
  Speakers will be determined automatically via biometrics.
  <Note>[Pro subscription](https://app.dubformer.ai/subscriptions) feature.</Note>

  **Cannot be used together with `source_script_content`.**

  Example:

  ```json theme={null}
  [
    { "start_ms": 0, "end_ms": 2000, "text": "Hello world" },
    { "start_ms": 2500, "end_ms": 5000, "text": "How are you?" }
  ]
  ```
</ParamField>

<ParamField body="use_fixed_timings" type="boolean" optional default="false">
  When `true`, source timings from `source_script` will be preserved (no alignment or rechunking).
  Useful when providing pre-translated scripts with `source_lang` = `target_lang`.
</ParamField>

<ParamField body="glossary_content" type="string" optional>
  Translation glossary in TSV format to ensure consistent terminology.
  <Note>[Pro subscription](https://app.dubformer.ai/subscriptions) feature.</Note>
</ParamField>

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

## Response

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

<ResponseField name="cost_minutes" type="number">
  Number of minutes charged for this project.
</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 after this project.
</ResponseField>

<ResponseField name="translations_count" type="number">
  Number of translations created (always 0 for new projects).
</ResponseField>

<ResponseExample>
  ```json Success Response theme={null}
  {
    "project_id": "12345",
    "cost_minutes": 10,
    "estimated_completion_date": "2024-06-05T12:00:00Z",
    "balance_minutes": 90,
    "translations_count": 0
  }
  ```
</ResponseExample>