soniox
Installation
SKILL.md
Soniox Voice AI Platform
Cloud speech-to-text and text-to-speech APIs with real-time WebSocket streaming, async file transcription, and a complete voice agent framework. Supports 60+ languages, speaker diarization, live translation, and custom vocabulary context.
API Structure
| API | Transport | Model | Use Case |
|---|---|---|---|
| STT Real-Time | WebSocket wss://stt-rt.soniox.com/transcribe-websocket |
stt-rt-v4 |
Live audio streaming, token-by-token results |
| STT Async | REST https://api.soniox.com/v1/ |
stt-async-v4 |
Pre-recorded files, batch processing |
| TTS Real-Time | WebSocket wss://tts-rt.soniox.com/tts-websocket |
tts-rt-v1-preview |
Streaming speech synthesis |
Authentication: Authorization: Bearer <API_KEY> header (or api_key query param for WebSocket).