xAI

This page is auto-generated from model configurations. Last updated: 2026-03-18.

This reference lists all available xAI audio generation models and their parameters. Use these parameter names when calling the Generation API.


xAI Grok TTS

Convert text to natural-sounding speech using xAI's Grok TTS with multiple voices, codecs, and multilingual support including speech tags like [pause] and <whisper>.

Model ID: model_xai-grok-tts

Capabilities: txt2audio

LLM Markdown: https://app.scenario.com/api/models/model_xai-grok-tts/markdown

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
textstringYes----Text to synthesize. Max 15,000 characters. Supports speech tags like [pause], <whisper>text</whisper>
voicestringNoeve--ara, eve, leo, rex, salVoice to use for synthesis
languagestringNoauto--auto, ar, bn, zh, en, fr, de, hi, id, it, ja, ko, pt, ru, es, tr, viLanguage code (BCP-47) or 'auto' for automatic detection
sampleRatenumberNo44100--8000, 16000, 22050, 24000, 44100, 48000Audio sample rate in Hz