The original title is: "xAI Grok audio models now available on Vercel AI Gateway"

Short summary

xAI's audio models (voice, text-to-speech, speech-to-text) are now available on Vercel AI Gateway. Developers can mint tokens for client-side security, use React hooks for WebSocket voice connections, and test in the browser playground. Models include grok-voice-think-fast-1.0 for realtime, grok-tts for speech synthesis, and grok-stt for transcription.

• •Three audio models now live: realtime voice, text-to-speech, and speech-to-text
• •Full AI SDK integration with token auth, React hooks, and playground testing
• •Accessible through Vercel AI Gateway with same routing and observability as other models

Generated with AI, which can make mistakes.