API Reference — STT
Speech to Text API
Complete endpoint reference for the ShunyaLabs ASR API. Batch transcription via HTTP POST, real-time streaming via WebSocket, and speaker management endpoints.
Base URLs
| Endpoint | URL |
|---|---|
| Batch Transcription | POST https://asr.shunyalabs.ai/v1/audio/transcriptions |
| Streaming (WebSocket) | wss://asr.shunyalabs.ai/ws |
| Health Check | GET https://asr.shunyalabs.ai/health |
| Supported Languages | GET https://asr.shunyalabs.ai/languages |
| Register Speaker | POST https://asr.shunyalabs.ai/v1/speakers/register |
| List Speakers | GET https://asr.shunyalabs.ai/v1/speakers/list |
| Identify Speaker | POST https://asr.shunyalabs.ai/v1/speakers/identify |
| Delete Speaker | DELETE https://asr.shunyalabs.ai/v1/speakers/delete |
Authentication
All endpoints except /health require a Bearer token:
http
Authorization: Bearer <API_KEY>Endpoints
Batch Transcription →
POST /v1/audio/transcriptions — Send audio files or URLs for transcription.
Streaming WebSocket →
WSS /ws — Real-time transcription over a persistent WebSocket connection.
Speaker APIs →
Register, list, identify, and delete speakers for speaker identification.
Health Check →
GET /health — Check API availability and backend readiness.