Text to Speech

Endpoint for text-to-speech conversion. Converts input text to speech audio using a specified speaker voice. Args: request (Request): The incoming HTTP request object. tts_request (TTSRequest): The request body containing text, speaker ID, and synthesis parameters. db (AsyncSession, optional): Database session dependency. current_user (User, optional): The authenticated user making the request. Returns: dict: A dictionary containing the generated speech audio with signed URL and metadata. Raises: HTTPException: Returns 503 if the service is unavailable due to timeout or connection error. HTTPException: Returns 500 for any other internal server errors. Speaker IDs: 241: Acholi (female) 242: Ateso (female) 243: Runyankore (female) 245: Lugbara (female) 246: Swahili (male) 248: Luganda (female) Example Response: { "output": { "audio_url": "https:...", "blob": "tts/20251003082338_f2ff97b3-9cb9-42fb-850d-0657f51e539e.mp3", "sample_rate": 16000 } }

POST /tasks/tts

Text To Speech

cURL

curl --request POST \
  --url https://api.sunbird.ai/tasks/tts \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "text": "<string>",
  "speaker_id": 248,
  "temperature": 0.7,
  "max_new_audio_tokens": 2000
}
'

422

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>"
    }
  ]
}

Authorizations

Authorization · string · header · required

The access token received from the authorization server in the OAuth 2.0 flow.

Body

application/json

text · string · required

speaker_id · enum<integer> · default: 248

Available options: 241, 242, 243, 245, 246, 248

temperature · number · default: 0.7

max_new_audio_tokens · integer · default: 2000

Response

200

application/json

Successful Response