Voice Changer

Upload an audio file, choose the target voice, and process the transformation as an async task. The result comes back as a finished audio URL once the task is done.

Endpoint

http

POST https://api.cheapaiapi.com/v1/task/voice-changer

Send the request as multipart/form-data.

Request Fields

filefilerequiredSource audio in MP3, M4A, or WAV.

voice_idstringrequiredTarget voice id from your available voice inventory.

model_idstringSpeech-to-speech model, usually eleven_multilingual_sts_v2.

voice_settingsjson stringOptional stability, similarity_boost, style, and speaker boost controls.

remove_background_noisebooleanWhether to remove background noise before conversion.

Example Request

bash

curl -X POST "https://api.cheapaiapi.com/v1/task/voice-changer" \
  -H "Authorization: Bearer sk_your_api_key" \
  -F 'file=@audio.mp3' \
  -F 'voice_id=21m00Tcm4TlvDq8ikWAM' \
  -F 'model_id=eleven_multilingual_sts_v2' \
  -F 'voice_settings={"stability":0.5,"similarity_boost":0.75,"style":0.2,"use_speaker_boost":true}' \
  -F 'remove_background_noise=true'

Task Pattern

json

{
  "success": true,
  "task_id": "uuid_task_id",
  "ec_remain_credits": 9500
}

After submission, poll the common task endpoint:

http

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

Completed Task Example

json

{
  "id": "uuid_task_id",
  "status": "done",
  "credit_cost": 5000,
  "metadata": {
    "audio_url": "https://example.com/transformed.mp3"
  },
  "type": "voice_changer"
}

What To Surface In UI

The chosen target voice before submit
Whether background noise removal is enabled
Advanced tuning settings only when the user asks for them
A clean audio preview once the task is complete