Voiceovers

GET /voices

List available voices for voiceover generation. Use the returned voice id when calling the text-to-speech or speech-to-speech endpoints.

Query Parameters

Response

{
  "data": [
    {
      "id": "uuid",
      "name": "Sarah",
      "gender": "female",
      "age_group": "adult",
      "accent": "american",
      "style": "professional",
      "preview_audio_url": "https://..."
    }
  ],
  "pagination": { "total": 15, "limit": 20, "offset": 0 }
}

Examples

curl "https://www.adsumo.ai/api/v1/voices?gender=female&style=professional" \
  -H "Authorization: Bearer adsumo_sk_..."

POST /voiceovers/text-to-speech

Generate a voiceover from text using ElevenLabs voices.

Request Body

Response

This endpoint returns a synchronous response. Unlike video and image generation endpoints, no webhook or polling is required.

{
  "id": "uuid",
  "status": "completed",
  "duration": 4.5,
  "audio_url": "https://..."
}

Note: audio_url is a temporary presigned URL that expires after 1 hour. Download and store the file if you need to access it later.

Credit Cost

1 credit per voiceover.

Examples

curl -X POST https://www.adsumo.ai/api/v1/voiceovers/text-to-speech \
  -H "Authorization: Bearer adsumo_sk_..." \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Welcome to our product launch. We are excited to share what we have been building.",
    "voice_id": "EXAVITQu4vr4xnSDxMaL",
    "model": "eleven_multilingual_v2",
    "voice_settings": {
      "stability": 0.5,
      "similarity_boost": 0.75
    }
  }'

POST /voiceovers/speech-to-speech

Clone or convert voice style from an audio file.

Request Body

Response

This endpoint returns a synchronous response, identical in shape to text-to-speech.

{
  "id": "uuid",
  "status": "completed",
  "duration": 4.5,
  "audio_url": "https://..."
}

Note: audio_url is a temporary presigned URL that expires after 1 hour. Download and store the file if you need to access it later.

Credit Costs

Credits are based on the duration of the source audio.