Voice Overview

import WebSocket from "ws";

const ws = new WebSocket("wss://api.x.ai/v1/realtime?model=grok-voice-latest", {
  headers: { Authorization: `Bearer ${process.env.XAI_API_KEY}` },
});

ws.on("open", () => {
  // Configure voice and enable tools
  ws.send(JSON.stringify({
    type: "session.update",
    session: {
      voice: "eve",
      instructions: "You are a helpful customer support agent.",
      turn_detection: { type: "server_vad" },
      tools: [{ type: "web_search" }]
    }
  }));
});

ws.on("message", (data) => {
  const event = JSON.parse(data);
  if (event.type === "response.output_audio.delta") {
    // Play audio: Buffer.from(event.delta, "base64")
  }
});

curl -X POST https://api.x.ai/v1/tts \
  -H "Authorization: Bearer $XAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Welcome to xAI. How can I help you today?",
    "voice_id": "eve",
    "language": "en"
  }' \
  --output welcome.mp3

import fs from "fs";

const response = await fetch("https://api.x.ai/v1/tts", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.XAI_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    text: "Welcome to xAI. How can I help you today?",
    voice_id: "eve",
    language: "en",
  }),
});

const buffer = Buffer.from(await response.arrayBuffer());
fs.writeFileSync("welcome.mp3", buffer);

curl -X POST https://api.x.ai/v1/stt \
  -H "Authorization: Bearer $XAI_API_KEY" \
  -F model=grok-voice-transcribe-2.0 \
  -F file=@recording.mp3

import fs from "fs";

const formData = new FormData();
formData.append("model", "grok-voice-transcribe-2.0");
formData.append("file", new Blob([fs.readFileSync("recording.mp3")]), "recording.mp3");

const response = await fetch("https://api.x.ai/v1/stt", {
  method: "POST",
  headers: { Authorization: `Bearer ${process.env.XAI_API_KEY}` },
  body: formData,
});

const result = await response.json();
console.log(result.text);

# 1. Create a custom voice from a reference audio clip (max 120s).
curl -X POST https://api.x.ai/v1/custom-voices \
  -H "Authorization: Bearer $XAI_API_KEY" \
  -F "name=Friendly Narrator" \
  -F "language=en" \
  -F "file=@reference.wav;type=audio/wav"

# Response: { "voice_id": "nlbqfwie", ... }

# 2. Use the custom voice for TTS.
curl -X POST https://api.x.ai/v1/tts \
  -H "Authorization: Bearer $XAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Hello! This is my custom voice.",
    "voice_id": "nlbqfwie",
    "language": "en"
  }' \
  --output custom.mp3

import fs from "fs";

// 1. Create a custom voice from a reference audio clip (max 120s).
const form = new FormData();
form.append("file", new Blob([fs.readFileSync("reference.wav")]), "reference.wav");
form.append("name", "Friendly Narrator");
form.append("language", "en");

const create = await fetch("https://api.x.ai/v1/custom-voices", {
  method: "POST",
  headers: { Authorization: `Bearer ${process.env.XAI_API_KEY}` },
  body: form,
});
const { voice_id } = await create.json();

// 2. Use the custom voice for TTS.
const speech = await fetch("https://api.x.ai/v1/tts", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.XAI_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    text: "Hello! This is my custom voice.",
    voice_id,
    language: "en",
  }),
});
fs.writeFileSync("custom.mp3", Buffer.from(await speech.arrayBuffer()));