Audio Dubbing

Upload an audio file, choose the target language, and treat dubbing as a task-based workflow. The final result can include dubbed audio and subtitle outputs.

Endpoint

http

POST https://api.cheapaiapi.com/v1/task/dubbing

Send this request as multipart/form-data.

Request Fields

filefilerequiredInput audio file such as mp3 or m4a.

target_langstringrequiredLanguage to dub into.

source_langstringOptional source language. Defaults to auto detection.

num_speakersintegerSpeaker count. Use 0 for automatic detection.

disable_voice_cloningbooleanUse a library voice instead of cloning when supported.

receive_urlstringOptional webhook for result delivery.

Example Request

bash

curl -X POST "https://api.cheapaiapi.com/v1/task/dubbing" \
  -H "Authorization: Bearer sk_your_api_key" \
  -F 'file=@podcast.mp3' \
  -F 'num_speakers=0' \
  -F 'disable_voice_cloning=false' \
  -F 'source_lang=auto' \
  -F 'target_lang=Spanish' \
  -F 'receive_url=https://your-app.com/webhooks/dubbing'

Task Pattern

json

{
  "success": true,
  "task_id": "uuid_task_id",
  "ec_remain_credits": 123456
}

Use the common task endpoint for status checks:

http

GET https://api.cheapaiapi.com/v1/task/{task_id}

Completed Task Example

json

{
  "id": "uuid_task_id",
  "status": "done",
  "credit_cost": 1,
  "metadata": {
    "audio_url": "https://example.com/audio.mp3",
    "srt_url": "https://example.com/audio.srt",
    "json_url": "https://example.com/audio.json"
  },
  "type": "dubbing"
}

What To Surface In UI

Target language selection before upload starts
Speaker detection mode versus explicit speaker count
Whether cloned or library voices are preferred for the dubbing run
Both dubbed audio and subtitle downloads when the task is complete