realtime-audio vercel-ai-gateway xai-grok speech-to-text voice-agents

xAI Grok audio models ship on Vercel AI Gateway

Realtime voice, TTS, and STT from xAI route through Vercel's gateway with token-based client auth and unified observability—integrate via AI SDK 7.

Summary

Eliminates API key exposure on client and consolidates audio infrastructure into existing gateway spend controls. Realtime voice agents now require only server token endpoint and browser hook.

Why it matters

Eliminates API key exposure on client and consolidates audio infrastructure into existing gateway spend controls. Realtime voice agents now require only server token endpoint and browser hook.

Implementation verdict

Replaces direct xAI audio integration with routed, metered access. Requires AI SDK 7, a token endpoint, and `useRealtime` hook. Ready now—playground test available before committing.

Sources

1.xAI's audio models are now live on AI Gateway
2.Realtime voice, text to speech, and speech to text are all available through the AI SDK with the same routing, observability, and spend controls as your other models
3.These capabilities are available on the AI SDK 7 release
4.A voice agent has two pieces: a server route that mints a short-lived token, so your API key never reaches the client, and a browser component that connects with it

Dev Signal

Get briefs like this in your inbox — free, every weekday.

100+ sources compressed into one 4-minute read. Ranked, cited, implementation-ready.

Read the full issue →All briefs