Soniox API reference

Base URLs

API base URLs depend on two factors: the specific service you are calling (Speech-to-Text, Text-to-Speech, Authentication) and your project's region.

For a complete list of regional domains (e.g., US, EU, Japan) and their corresponding REST and WebSocket endpoints, please refer to our Data residency guide.

---

REST API

OpenAPI schema: https://soniox.com/docs/openapi.yaml

Authentication

Create and manage API keys for authentication.

• Create temporary API key: Create short-lived API keys.

Speech-to-Text

REST API for Speech-to-Text is available at https://api.soniox.com/v1 and includes:

• Files: Manage audio files by uploading, listing, retrieving, and deleting them.
• Transcriptions: Create and manage transcriptions for audio files.
• STT models: List available STT models.

See Get started for an introduction.

Text-to-Speech

REST API for Text-to-Speech is available at https://tts-rt.soniox.com/tts.

• Generate TTS: Synthesize speech from text.
• TTS models: List available TTS models.

See Get started for an introduction.

---

Errors

REST API responses and async transcription failures carry a stable error_type you can branch on in code. The WebSocket APIs currently return only an HTTP status code (error_code) and a human-readable error_message. See the Errors reference for the full list of error types, their causes, and how to resolve them.

---

WebSocket API

Realtime Speech-to-Text

Use WebSocket API to transcribe and translate live audio streams in real-time.

• Endpoint: wss://stt-rt.soniox.com
• Reference: WebSocket API

Realtime Text-to-Speech

Use WebSocket API for low-latency, streaming speech synthesis.

• Endpoint: wss://tts-rt.soniox.com/tts-websocket
• Reference: WebSocket API