← All models
Build real-time voice applications powered by Grok. Stream audio and text bidirectionally via WebSocket for voice assistants, phone agents, and interactive voice systems.
Details
- Accepts
- text
Pricing
- Price
- 0.104 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| typerequired | string | xAI realtime event type (e.g. 'session.update', 'input_audio_buffer.append', 'response.create', 'response.output_audio.delta'). Events are relayed verbatim in both directions. |
| tools | — | Server-side tools available to the agent. Web, X, and remote MCP tools are supported; every tool is disabled by default. An explicitly supplied object always reaches the session, so previously enabled tools can be cleared. |
| voice | — | Built-in xAI voice for the agent's speech. Uses Grok's default voice when omitted. |
| prompt | — | System instructions describing the agent's persona and conversation context. Uses Grok's default persona when omitted. |
| turn_detection | — | Automatic turn detection: any configured object (even empty) lets the agent detect when you stop speaking and reply on its own. Set null for manual turns; omit to keep the session default. |
Output
| Field | Type | Description |
|---|---|---|
| type | string | xAI realtime event type (e.g. 'session.update', 'input_audio_buffer.append', 'response.create', 'response.output_audio.delta'). Events are relayed verbatim in both directions. |
| tools | — | Server-side tools available to the agent. Web, X, and remote MCP tools are supported; every tool is disabled by default. An explicitly supplied object always reaches the session, so previously enabled tools can be cleared. |
| voice | — | Built-in xAI voice for the agent's speech. Uses Grok's default voice when omitted. |
| prompt | — | System instructions describing the agent's persona and conversation context. Uses Grok's default persona when omitted. |
| turn_detection | — | Automatic turn detection: any configured object (even empty) lets the agent detect when you stop speaking and reply on its own. Set null for manual turns; omit to keep the session default. |