import asyncio
import os

from dotenv import load_dotenv
from elevenlabs import AsyncElevenLabs

load_dotenv()

elevenlabs = AsyncElevenLabs(api_key=os.getenv("ELEVENLABS_API_KEY"))

async def main():
    engine = await elevenlabs.speech_engine.create(
        name="My Speech Engine",
        speech_engine={"ws_url": os.environ["PUBLIC_WS_URL"]},
    )
    print(engine.engine_id)

asyncio.run(main())

import { ElevenLabsClient } from "@elevenlabs/elevenlabs-js";
import "dotenv/config";

const elevenlabs = new ElevenLabsClient({
  apiKey: process.env.ELEVENLABS_API_KEY,
});

const engine = await elevenlabs.speechEngine.create({
  name: "My Speech Engine",
  speechEngine: { wsUrl: process.env.PUBLIC_WS_URL! },
});

console.log(engine.engineId);

import asyncio
import os

from dotenv import load_dotenv
from elevenlabs import AsyncElevenLabs
from openai import AsyncOpenAI

load_dotenv()

elevenlabs = AsyncElevenLabs(api_key=os.getenv("ELEVENLABS_API_KEY"))
openai = AsyncOpenAI(api_key=os.getenv("OPENAI_API_KEY"))

async def on_transcript(transcript, session):
    stream = await openai.responses.create(
        model=os.environ["OPENAI_MODEL"],
        instructions="You are a concise, conversational voice assistant.",
        input=[
            {
                "role": "assistant" if message.role == "agent" else message.role,
                "content": message.content,
            }
            for message in transcript
        ],
        stream=True,
    )
    await session.send_response(stream)

async def main():
    engine = await elevenlabs.speech_engine.get(os.environ["ELEVENLABS_SPEECH_ENGINE_ID"])
    await engine.serve(
        port=3001,
        path="/ws",
        debug=True,
        on_transcript=on_transcript,
    )

asyncio.run(main())

import { ElevenLabsClient } from "@elevenlabs/elevenlabs-js";
import { createServer } from "node:http";
import OpenAI from "openai";
import "dotenv/config";

const elevenlabs = new ElevenLabsClient({
  apiKey: process.env.ELEVENLABS_API_KEY,
});
const openai = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });
const httpServer = createServer();

await elevenlabs.speechEngine.attach(
  process.env.ELEVENLABS_SPEECH_ENGINE_ID!,
  httpServer,
  "/ws",
  {
    debug: true,
    async onTranscript(transcript, signal, session) {
      const response = await openai.responses.create(
        {
          model: process.env.OPENAI_MODEL!,
          instructions: "You are a concise, conversational voice assistant.",
          input: transcript.map((message) => ({
            role: message.role === "agent" ? "assistant" : message.role,
            content: message.content,
          })),
          stream: true,
        },
        { signal },
      );

      session.sendResponse(response);
    },
  },
);

httpServer.listen(3001);

import express from "express";
import { ElevenLabsClient } from "@elevenlabs/elevenlabs-js";
import "dotenv/config";

const app = express();
const elevenlabs = new ElevenLabsClient();

app.get("/api/token", async (_req, res) => {
  const response = await elevenlabs.conversationalAi.conversations.getWebrtcToken({
    agentId: process.env.ELEVENLABS_SPEECH_ENGINE_ID!,
  });
  res.json({ token: response.token });
});

import { useConversation } from "@elevenlabs/react";

export function VoiceControls() {
  const conversation = useConversation({
    onConnect: () => console.log("connected"),
    onDisconnect: () => console.log("disconnected"),
    onError: (error) => console.error(error),
  });

  async function startConversation() {
    await navigator.mediaDevices.getUserMedia({ audio: true });
    const { token } = await fetch("/api/token").then((res) => res.json());

    await conversation.startSession({
      conversationToken: token,
      overrides: {
        agent: { firstMessage: "Hello! How can I help you today?" },
      },
    });
  }

  return <button onClick={startConversation}>Start conversation</button>;
}

{
  "overrides": {
    "livekit-client": "2.16.1"
  }
}