# Grok Voice Think Fast 1.0

Grok Voice Think Fast 1.0 powers voice agents that listen and respond in real time. Audio streams both ways over a WebSocket session through AI Gateway, with background reasoning keeping replies responsive.

- **Model ID:** `spacexai/grok-voice-think-fast-1.0`
- **Type:** realtime
- **Providers:** xai
- **Context window:** Not applicable
- **Maximum output tokens:** 0
- **Pricing:** See the provider details below
- **Canonical page:** https://vercel.com/ai-gateway/models/grok-voice-think-fast-1.0

## Supported parameters

Detailed capability metadata has not been reported for this model.

## Example

```ts
import { gateway } from '@ai-sdk/gateway';

export async function POST() {
  const { token, url } = await gateway.experimental_realtime.getToken({
    model: 'spacexai/grok-voice-think-fast-1.0',
  });

  return Response.json({ token, url, tools: [] });
}
```

## About

Grok Voice Think Fast 1.0 is SpaceXAI's realtime voice model, released April 23, 2026 and available through AI Gateway. Grok Voice Think Fast 1.0 handles full-duplex, speech-to-speech conversation: audio streams in, and spoken replies stream back with low latency. Background reasoning lets Grok Voice Think Fast 1.0 think through hard queries while the conversation keeps moving. SpaceXAI positions the model for customer support, sales, and other high-stakes voice workflows.

Grok Voice Think Fast 1.0 captures structured data from natural speech, including email addresses, street addresses, phone numbers, and account numbers, even through accents and mid-sentence corrections. Tool calling works inside the session, so a voice agent can act on external systems mid-conversation. SpaceXAI reports support for conversations in more than 25 languages and robustness under telephony conditions like noise and interruptions.

Through AI Gateway, a server route mints a short-lived token with `gateway.experimental_realtime.getToken`, so your API key never reaches the client. In the browser, the `useRealtime` hook from `@ai-sdk/react` manages the WebSocket connection, microphone capture, and audio playback. In Node.js, the realtime model acts as a codec for a WebSocket you drive yourself. Session config covers voice, turn detection, instructions, and tools. Realtime support ships on the canary releases of the AI SDK.

## What to consider

Grok Voice Think Fast 1.0 supports speech-to-speech only. Transcription and translation aren't handled in realtime sessions, so use `grok-stt` for recorded audio. Image input isn't supported either.

AI Gateway enforces session limits: 25 minutes maximum duration, a five-minute idle timeout, and a cap on concurrent sessions per team. Reconnecting doesn't resume a previous session, so replay any context you need after a drop. Realtime support is experimental and ships on canary AI SDK releases, so expect API changes.

## When to use

### Best For

- **Voice assistants and agents** needing full-duplex conversation with spoken replies in real time
- **Phone and support lines** with robust handling of noise, accents, and interruptions on telephony audio
- **Structured data capture** collecting emails, addresses, and account numbers from natural speech
- **Tool-calling voice workflows** where session tools let agents act on external systems mid-conversation
- **Multilingual voice apps** holding conversations in more than 25 languages

### Consider Alternatives When

- **Recorded audio transcription** where `grok-stt` transcribes files, since realtime sessions are speech-to-speech only
- **One-way speech output** where `grok-tts` generates narration without a live session
- **Long uninterrupted sessions** since AI Gateway caps realtime sessions at 25 minutes

## Best for

- **Voice Assistants and Agents:** Full-duplex conversation with spoken replies in real time
- **Phone and Support Lines:** Robust handling of noise, accents, and interruptions on telephony audio
- **Structured Data Capture:** Collects emails, addresses, and account numbers from natural speech
- **Tool-Calling Voice Workflows:** Session tools let agents act on external systems mid-conversation
- **Multilingual Voice Apps:** Conversations in more than 25 languages

## Consider alternatives

- **Recorded Audio Transcription:** `grok-stt` transcribes files, since realtime sessions are speech-to-speech only
- **One-Way Speech Output:** `grok-tts` generates narration without a live session
- **Long Uninterrupted Sessions:** AI Gateway caps realtime sessions at 25 minutes, so plan reconnect logic

## Frequently asked questions

### How do I connect to Grok Voice Think Fast 1.0 through AI Gateway?

Add a server route that mints a short-lived token with `gateway.experimental_realtime.getToken`. In the browser, the `useRealtime` hook from `@ai-sdk/react` handles the WebSocket connection, microphone capture, and playback. In Node.js, drive a WebSocket yourself using the realtime model as a codec.

### Can Grok Voice Think Fast 1.0 transcribe or translate audio?

No. Grok Voice Think Fast 1.0 supports speech-to-speech only. Use `grok-stt` to transcribe recorded audio.

### What session limits apply to Grok Voice Think Fast 1.0?

AI Gateway caps sessions at 25 minutes, closes idle sessions after five minutes, expects a first client message within 30 seconds, and rejects messages over 256 KB. Teams also have a concurrent session limit.

### What is background reasoning in Grok Voice Think Fast 1.0?

Background reasoning lets Grok Voice Think Fast 1.0 work through hard queries while the conversation continues, so spoken replies stay responsive during complex, multi-step requests.

### What languages does Grok Voice Think Fast 1.0 support?

SpaceXAI reports support for conversations in more than 25 languages, with robustness under telephony conditions like noise, accents, and interruptions.

### What does Grok Voice Think Fast 1.0 cost?

See the pricing section on this page for today's rates. AI Gateway exposes current pricing for Grok Voice Think Fast 1.0.

### How do I authenticate with Grok Voice Think Fast 1.0 through Vercel AI Gateway?

Use your Vercel AI Gateway API key on the server with `spacexai/grok-voice-think-fast-1.0` as the model identifier. `getToken` exchanges the key for a single-use, short-lived client secret, so the key never reaches the browser.

### Does Vercel AI Gateway support Zero Data Retention for Grok Voice Think Fast 1.0?

Yes, Zero Data Retention is available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.

## Links

- [Model page](https://vercel.com/ai-gateway/models/grok-voice-think-fast-1.0)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://docs.x.ai/developers/model-capabilities/audio/voice-agent)


If you encounter incorrect information, can’t find what you need, need a capability Vercel doesn’t currently offer, or have any other feedback to report, please do it by following the instructions at https://vercel.com/feedback.md.