Repository Public
1<!-- source: https://docs.x.ai/developers/models/text-to-speech (from https://docs.x.ai/llms-full.txt, retrieved 2026-09-19T05:28:55Z) -->2#### Models34# Text to Speech56The Text to Speech API converts text into natural speech, billed per input character. Supports a full lineup of expressive voices, streaming, and batch output, in MP3, WAV, PCM, μ-law, and A-law formats.78## At a glance910| | Details |11|---|---|12| **Modalities** | Text → Audio |13| **Pricing** | / 1M chars |14| **Region** | us-east-1 |1516## Pricing1718| | Details |19|---|---|20| **Per 1M chars** | / 1M chars |2122## Rate Limits2324| | Details |25|---|---:|26| **Requests per second** | RPS |27| **Concurrent sessions** | per team |2829## Capabilities3031* Expressive built-in voices32* Streaming output33* Batch output34* MP3 / WAV / PCM / μ-law / A-law formats3536## Availability3738| | Details |39|---|---|40| **Cluster** | us-east-1 |4142## Documentation4344* [Text to Speech Guide](/developers/model-capabilities/audio/text-to-speech) — Getting started with text to speech45* [API Reference](/developers/rest-api-reference/inference/voice#text-to-speech---rest) — Text to Speech endpoint reference46* [Pricing](/developers/pricing#voice-api-pricing) — Full pricing overview47