xAI’s Grok voice APIs land on Vercel AI Gateway with realtime, TTS, and STT support
Developers can now access Grok's full voice stack through a single unified gateway, no separate API keys required
SpaceXAI, the AI division formed after xAI’s integration into SpaceX, has added its Grok voice models to the Vercel AI Gateway. The move gives developers access to a full voice stack, including realtime voice, text-to-speech, and speech-to-text, through a single API layer that already handles routing, observability, and budget controls.
The announcement landed on June 29, 2026, with Vercel posting the update to its changelog and xAI officials amplifying it on X. The framing from both sides was direct: “state of the art voice APIs from SpaceXAI” are now live on the Gateway.
What’s actually in the box
Three models shipped with the integration. The realtime voice model is listed as xai/grok-voice-think-fast-1.0, designed for low-latency, bidirectional interactions. Then there’s xai/grok-tts for text-to-speech and xai/grok-stt for speech-to-text.
Bidirectional WebSocket streaming is baked in, which is the technical requirement for anything resembling a real phone call or live voice assistant.
No separate xAI API keys are needed when routing through the Vercel AI Gateway. Developers who already work inside the Vercel ecosystem can access the Grok voice stack without juggling another credential or onboarding to a separate platform.
The integration runs on AI SDK 7, Vercel’s latest release of its developer toolkit. Earlier Grok models covering text, image, and video processing were already available on the Gateway before this voice expansion, meaning xAI’s footprint on the platform has now grown to cover the full multimodal picture.
The SpaceXAI context
xAI, Elon Musk’s AI company behind the Grok models, completed its integration into SpaceX in May 2026, resulting in the SpaceXAI branding that now appears on these APIs.
The Vercel AI Gateway emerged in alpha in May 2025 and provides a streamlined endpoint for developers, facilitating access to a multitude of AI models with features such as intelligent routing, failover, and analytics.
What this means for developers and the market
The budget controls built into the Gateway are worth flagging for teams at companies with finance oversight. Voice APIs can burn through credits fast in high-traffic applications. Having hard budget limits enforced at the gateway layer, rather than relying on application-level logic, is the kind of guardrail that gets enterprise procurement teams comfortable signing off on a new vendor.