Integrate your own model

Connect an agent to your own LLM or host your own server.

Define the Extra Parameters

Create an object containing your custom parameters:

Python

from elevenlabs.conversational_ai.conversation import Conversation, ConversationInitiationData

extra_body_for_convai = {
    "UUID": "123e4567-e89b-12d3-a456-426614174000",
    "parameter-1": "value-1",
    "parameter-2": "value-2",
}

config = ConversationInitiationData(
    extra_body=extra_body_for_convai,
)

Update the LLM Implementation

Modify your custom LLM code to handle the additional parameters:

Python

import json
import os
import fastapi
from fastapi.responses import StreamingResponse
from fastapi import Request
from openai import AsyncOpenAI
import uvicorn
import logging
from dotenv import load_dotenv
from pydantic import BaseModel
from typing import List, Optional

# Load environment variables from .env file
load_dotenv()

# Retrieve API key from environment
OPENAI_API_KEY = os.getenv('OPENAI_API_KEY')
if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY not found in environment variables")

app = fastapi.FastAPI()
oai_client = AsyncOpenAI(api_key=OPENAI_API_KEY)

class Message(BaseModel):
    role: str
    content: str

class ChatCompletionRequest(BaseModel):
    messages: List[Message]
    model: str
    temperature: Optional[float] = 0.7
    max_tokens: Optional[int] = None
    stream: Optional[bool] = False
    user_id: Optional[str] = None
    elevenlabs_extra_body: Optional[dict] = None

@app.post("/v1/chat/completions")
async def create_chat_completion(request: ChatCompletionRequest) -> StreamingResponse:
    oai_request = request.dict(exclude_none=True)
    print(oai_request)
    if "user_id" in oai_request:
        oai_request["user"] = oai_request.pop("user_id")

    if "elevenlabs_extra_body" in oai_request:
        oai_request.pop("elevenlabs_extra_body")

    chat_completion_coroutine = await oai_client.chat.completions.create(**oai_request)

    async def event_stream():
        try:
            async for chunk in chat_completion_coroutine:
                chunk_dict = chunk.model_dump()
                yield f"data: {json.dumps(chunk_dict)}\n\n"
            yield "data: [DONE]\n\n"
        except Exception as e:
            logging.error("An error occurred: %s", str(e))
            yield f"data: {json.dumps({'error': 'Internal error occurred!'})}\n\n"

    return StreamingResponse(event_stream(), media_type="text/event-stream")

if __name__ == "__main__":
    uvicorn.run(app, host="0.0.0.0", port=8013)

Example Request

With this custom message setup, your LLM will receive requests in this format:

JSON

{
  "messages": [
    {
      "role": "system",
      "content": "\n  <Redacted>"
    },
    {
      "role": "assistant",
      "content": "Hey I'm currently unavailable."
    },
    {
      "role": "user",
      "content": "Hey, who are you?"
    }
  ],
  "model": "gpt-4o",
  "temperature": 0.5,
  "max_tokens": 5000,
  "stream": true,
  "elevenlabs_extra_body": {
    "UUID": "123e4567-e89b-12d3-a456-426614174000",
    "parameter-1": "value-1",
    "parameter-2": "value-2"
  }
}

server.ts

import express, { Request, Response } from "express";
import OpenAI from "openai";

const app = express();
app.use(express.json());

const openai = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });

interface InputMessage {
  role: string;
  content: string;
}

interface ResponseCreateRequest {
  model: string;
  input: InputMessage[];
  instructions?: string;
  temperature?: number;
  max_output_tokens?: number;
  stream?: boolean;
}

app.post("/v1/responses", async (req: Request, res: Response) => {
  const request = req.body as ResponseCreateRequest;

  res.setHeader("Content-Type", "text/event-stream");
  res.setHeader("Cache-Control", "no-cache");
  res.setHeader("Connection", "keep-alive");

  try {
    const stream = await openai.responses.create({
      model: request.model,
      input: request.input,
      instructions: request.instructions,
      temperature: request.temperature ?? 0.7,
      max_output_tokens: request.max_output_tokens,
      stream: true,
    });

    for await (const event of stream) {
      if (event.type === "response.output_text.delta") {
        res.write(
          `event: response.output_text.delta\ndata: ${JSON.stringify({ type: "response.output_text.delta", delta: event.delta })}\n\n`
        );
      } else if (event.type === "response.completed") {
        res.write(
          `event: response.completed\ndata: ${JSON.stringify({ type: "response.completed", response: { id: event.response.id, status: "completed" } })}\n\n`
        );
      }
    }

    res.write("data: [DONE]\n\n");
    res.end();
  } catch (error) {
    console.error("An error occurred:", error);
    res.write(
      `event: error\ndata: ${JSON.stringify({ type: "error", error: { message: String(error) } })}\n\n`
    );
    res.end();
  }
});

app.listen(8013, () => console.log("Server running on port 8013"));

Run this code or your own server code.

Search documentation

Help Center

Integrate your own model

Example Request

Help Center