xAI Grok audio models now available on Vercel AI Gateway
By Steven Van ·
Realtime voice, text-to-speech, and speech-to-text from xAI join AI SDK 7 with the same routing and spend controls as Vercel's other models.
xAI's audio models are now live on Vercel's AI Gateway, with the same routing, observability, and spend controls as its other models, according to the quickstart guide. The three capabilities ship through the AI SDK 7 release:
- Realtime voice (xai/grok-voice-think-fast-1.0): a server route mints a short-lived token so the API key never reaches the browser, and the useRealtime hook from @ai-sdk/react handles the WebSocket connection, microphone capture, and playback.
- Text to speech (xai/grok-tts): generated with the AI SDK's generateSpeech function, given a voice and output format.
- Speech to text (xai/grok-stt): transcribed with the AI SDK's transcribe function.
Vercel
The platform for frontend developers — deploy, preview, and scale web apps and AI agents with zero config.
View Vercel →