Text to Speech

Convert text into natural-sounding speech

The Text to Speech (TTS) service converts written text into spoken audio in various Ugandan languages.

Available Voices

We provide specific speaker models for each language to ensure natural intonation and pronunciation.

ID	Language	Gender	Characteristics
241	Acholi	Female	Clear, moderate pace
242	Ateso	Female	Warm, expressive
243	Runyankole	Female	Soft, natural
245	Lugbara	Female	Clear articulation
246	Swahili	Male	Deep, authoritative
248	Luganda	Female	Natural, conversational

Generating Speech

Use the /tasks/tts endpoint.

Parameters

Parameter	Type	Required	Description
text	string	Yes	The text to convert to speech.
speaker_id	integer	Yes	The ID of the voice to use (see table above).

Example Request

Generating Luganda speech.

Python

import requests

url = "https://api.sunbird.ai/tasks/tts"
payload = {
    "text": "Oli otya?",
    "speaker_id": 248
}
headers = {
    "Authorization": "Bearer <YOUR_TOKEN>",
    "Content-Type": "application/json"
}

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

Response

The response includes a URL to the generated audio file.

{
  "output": {
    "audio_url": "https://storage.googleapis.com/...",
    "sample_rate": 16000
  }
}

The audio_url is a temporary signed URL. You should download or stream the audio immediately.