Grok Voice is a real-time bidirectional voice agent for building conversational applications over WebSocket with low-latency turn-taking. It handles speech-to-speech interactions with automatic voice activity detection, supports 20+ languages with native-quality accents, and offers five voices (Eve, Ara, Rex, Sal, Leo) plus custom voice options. The model integrates tools including web search, X search, document retrieval, and custom function calling via JSON schema, enabling agents that fetch live data and take actions mid-conversation. It maintains session context for resumption (history is dropped after 30 minutes of inactivity), supports DTMF phone keypresses, and is compatible with the OpenAI Realtime API, which keeps migration straightforward for developers familiar with that standard. On independent benchmarks from Artificial Analysis, Grok Voice leads the Tau Voice Bench and scores 92.3% on Big Bench Audio for speech reasoning, surpassing Gemini 2.5 Flash Native Audio and GPT Realtime.
Call Grok Voice on Opper with the OpenAI SDK. Sign up without a credit card. Get started
Usage-based pricing, billed by the minute and tiered by variant, not by token.
| Variant | Price |
|---|---|
| Input | $0.025 / min |
| Output | $0.025 / min |
Grok Voice runs on 1 route through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below.
| Provider | Region | Zero data retention | Training | Price |
|---|---|---|---|---|
| US | No | from $0.025 / min |
Grok Voice runs on a single route through the Opper gateway today, so its availability is that provider's availability.
Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. Set up a fallback chain.
Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. See uptime for every provider Opper monitors.
Each route hosting Grok Voice has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs; DPA available.
Call Grok Voice through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.
Grok Voice is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.
Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.OPPER_API_KEY,baseURL: "https://api.opper.ai/v3/compat",});const completion = await client.chat.completions.create({model: "xai/grok-voice-latest",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
