xAI has released a Text to Speech API that converts text into natural speech. This API supports a range of expressive voices, streaming output, and batch output. It is available in MP3, WAV, PCM, μ-law, and A-law formats.
Key Points
- The Text to Speech API is billed per input character.
- Pricing for the Text to Speech API is $15.00 per 1 million characters.
- The API operates in the us-east-1 region.
- Rate limits are 50 requests per second and 100 concurrent sessions per team.
- The API supports expressive built-in voices, streaming output, and batch output.
- The API was last updated on July 23, 2026.
Context
According to xAI, the Text to Speech API is part of a broader suite of voice capabilities, which also includes Speech to Speech and Speech to Text APIs. The Speech to Speech API, for instance, enables real-time voice conversations over WebSocket, billed by minute of audio plus a flat fee per text input message, and supports function calling with web search, X search, collections, and custom functions. xAI also offers a Responses API for text generation, which allows for optional stateful interactions where previous prompts and responses are saved for 30 days.
Why It Matters
Developers can integrate natural speech generation into applications, offering capabilities such as audio content creation or voice interfaces. The specified pricing and rate limits provide clear parameters for planning and scaling usage.
What To Do
- Review the Text to Speech Guide for getting started with the API.
- Consult the API Reference for details on the Text to Speech endpoint.
- Compare the pricing details for Text to Speech with other xAI voice APIs.
- Note the rate limits for requests per second and concurrent sessions.