Skip to main content
The Speech to Text (STT) service allows you to transcribe audio files into text. It supports multiple Ugandan languages and English.

​
Supported Languages

LanguageCode
Acholiach
Atesoteo
Englisheng
Lugandalug
Lugbaralgg
Runyankolenyn

​
Audio Requirements

  • Formats: MP3, WAV, OGG, M4A, AAC
  • Duration Limit: Files are processed up to 10 minutes. Audio longer than 10 minutes will be trimmed to the first 10 minutes.
  • File Size: Direct uploads are supported for files up to 100MB.

​
Transcribing Audio

Use the /tasks/stt endpoint for standard uploads.

​
Example Request

import requests

url = "https://api.sunbird.ai/tasks/stt"
files = {
    'audio': open('recording.mp3', 'rb')
}
headers = {
    "Authorization": "Bearer <YOUR_TOKEN>"
}

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

​
Response

{
  "output": {
    "text": "This is the transcribed text from the audio file.",
    "language": "eng"
  }
}

​
Handling Large Files

For files larger than 100MB, or to bypass server timeouts, we recommend using the Upload URL workflow.
  1. Generate an Upload URL: Call /tasks/generate-upload-url to get a signed Google Cloud Storage URL.
  2. Upload File: PUT the file directly to that URL.
  3. Process: Call /tasks/stt_from_gcs with the blob name to start transcription.

Large File Upload Guide

See the API reference for detailed steps on handling large files.