Convert audio to text with high accuracy for Amharic, Tigrinya, and Somali using our ASR API.

Overview

Our ASR service transcribes audio files into text. You can transcribe single files or batch process multiple files. The service supports both synchronous (immediate) and asynchronous (background) processing.

Basic Transcription

To transcribe a single audio file:

curl https://api.lesan.ai/transcribe \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "audio_url": "https://example.com/audio.mp3",
    "language": "am",
    "mode": "sync"
  }'

Supported Languages

• am - Amharic
• ti - Tigrinya
• so - Somali
• en - English

Processing Modes

Synchronous (sync)

Process immediately and return the result. Best for short audio files (< 5 minutes).

Asynchronous (async)

Queue the job and return a job ID. Poll the job status endpoint to get results. Best for longer files.

Batch Processing

Process multiple audio files at once. Batch processing is always asynchronous:

curl https://api.lesan.ai/transcribe/batch \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "audio_urls": [
      "https://example.com/audio1.mp3",
      "https://example.com/audio2.mp3"
    ],
    "language": "am"
  }'

For detailed API documentation, see the API Reference.