Learn how to customize your AI agent for each conversation by adding personalized details and passing custom parameters. For example, greet users by their name, adjust responses based on account-specific data, or include metadata to enhance interactions.

​
What You’ll Need

​
Agent Conversation Overrides

In ElevenLabs Conversational AI, you typically define a top-level agent with default settings. This feature allows you to create tailored voice experiences, without creating new agents.

The following steps will show you how to configure the prompt & first_message on setup to greet the user by their name.

Ensure you have the latest Javascript/React SDK installed.

1

const conversation = await Conversation.startSession({
  ...
  overrides: {
      agent: {
          prompt: {
              prompt: `The customer's bank account balance is ${customer_balance}. They are based in ${customer_location}.`
          },
          first_message: `Hi ${customer_name}, how can I help you today?`,
      },
      tts: {
          voiceId: "" // override the voice id.
      }
  },
  ...
})

With this agent override feature, you can now create a single agent and customize it with every customer conversation.

​
Custom LLM Parameters

Similarly, you may pass additional parameters to your custom LLM implementation.

1

Define the Extra Parameters

Create an object containing your custom parameters:

from elevenlabs.conversational_ai.conversation import Conversation, ConversationConfig

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

config = ConversationConfig(
    extra_body=extra_body_for_convai,
)
2

Update the LLM Implementation

Modify your custom LLM code to handle the additional parameters:

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:

{
  "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"
  }
}

​
Troubleshooting

Was this page helpful?

Knowledge BasePython SDK