Sign in
← AI PulseJul 23, 2026

Wire · news · Single-source brief

xAI Introduces Speech to Speech API for Real-Time Voice Conversations

xAI has launched a new Speech to Speech API that facilitates real-time voice conversations over WebSocket, with billing based on audio duration and text input messages.

By Illumora Editorial

Source · Jul 22, 2026, 11:58 PM · On Illumora · Jul 23, 2026, 4:37 AM

Media from the primary source — shown here so you can stay on Illumora.

Rewritten from one allowlisted primary — not independent enterprise reporting. Lanes →

Brief drafted by Illumora’s editorial model from the linked primary source. Ops desk reviews flagged pieces. How we write →

Read the source →xAI Docs — Speech to Speech API | SpaceXAI Docs
Save

xAI has released a Speech to Speech API designed for real-time voice conversations. This API operates over WebSocket and supports function calling, including capabilities such as web search, X search, collections, MCP, and custom functions. Billing for the service is calculated by the minute of audio processed and a flat fee per text input message.

Key Points

  • The Speech to Speech API enables real-time voice conversations via WebSocket.
  • The API supports function calling for web search, X search, collections, MCP, and custom functions.
  • Audio processing is billed at $0.05 per minute (or $3.00 per hour).
  • Text input messages are billed at $0.004 per message for each conversation.item.create event.
  • The service is hosted in the us-east-1 region.
  • function_call_output items and items with input_audio or audio content are not billed as text input messages.

Context

According to xAI, the Speech to Speech API charges based on the duration of audio sent or received, and for text events that are sent without accompanying audio. Each conversation.item.create event sent from a client is billed, with specific exceptions for server-requested tool results and audio-content items.

Why It Matters

This API provides developers with a tool for integrating real-time voice interactions into applications, offering a structured pricing model for both audio and text components of conversations. The inclusion of function calling expands the utility of these voice interactions.

What To Do

  • Review the Speech to Speech API documentation for detailed integration instructions.
  • Test the API's capabilities in the provided Playground environment.
  • Note the pricing structure for audio and text inputs when planning application costs.
  • Explore the API reference for WebSocket endpoint details.

Keep Exploring

/atlas/grok-family