xAI: Grok Voice 3.0 API
Grok Voice 3.0 is xAI's real-time speech-to-speech model: it answers spoken input with speech in under a second, with interruptions, function calling and web search.
- Input: text, audio
- Output: text, audio
- Reasoning: Supported
- Tool calling: Supported
- Released: 2026-10-14
Frequently Asked Questions
Does Grok Voice 3.0 support function calling?
Yes. Grok Voice 3.0 supports tool / function calling.
Does Grok Voice 3.0 support reasoning?
Yes. Grok Voice 3.0 is a reasoning-capable model.