Add a face to your ElevenLabs agent

LemonSlice puts a lifelike, real-time avatar on top of the ElevenLabs voice stack. Whether you run ElevenLabs Agents or Eleven TTS inside your app, the interactive avatar turns that audio into natural, face-to-face conversation with your customers.

LemonSlice

At a glance

Categories
Voice agents, Voice (TTS)
Status
Compatible (works with any)
Type
Avatar API
Languages
Python, Node.js
Setup time
~5 minutes

How the integration works

ElevenLabs keeps doing what it does today. LemonSlice turns the audio into a face.

  1. Keep your ElevenLabs setup

    Your ElevenLabs Agents configuration or Eleven voice pipeline keeps running the conversation. Nothing about your prompts, voices, or tooling changes.

  2. Stream the audio to LemonSlice

    Pipe the audio output from ElevenLabs into the LemonSlice avatar API. LemonSlice renders the avatar in real time, with lip sync and expression matched to the speech.

  3. The avatar video streams to your users

    LemonSlice streams the rendered video back over WebRTC, natively via LiveKit, Daily (Pipecat), or Agora, so your users see a face responding in real time.

Add an interactive AI avatar in minutes

A ElevenLabs session with a LemonSlice avatar.

Choose a code example
from livekit import agents
from livekit.agents import AgentSession, RoomOutputOptions
from livekit.plugins import lemonslice

async def entrypoint(ctx: agents.JobContext):
    await ctx.connect()

    session = AgentSession(
        # Add ElevenLabs TTS, plus your STT and LLM, here
    )

    avatar = lemonslice.AvatarSession(
        # Publicly accessible image URL for the avatar
        agent_image_url="...",
        # Prompt to guide the avatar's demeanor while speaking
        agent_prompt="a person talking",
        # Recommended. Adapts video quality to each viewer's bandwidth
        simulcast=True,
    )

    # Start the avatar and wait for it to join
    session_id = await avatar.start(session, room=ctx.room)

    # Start your agent session with the user
    await session.start(
        # ... room, agent, room_options, etc....
    )

An interactive avatar built to connect

Control actions and emotions

The Action Engine animates the whole performance, face, hands, shoulders, and posture. You control actions and emotions directly through the API, down to a prompt like "talk with hand gestures."

Works with any character, in any style

LemonSlice stands alone in animating non-humans (a turtle, a smiling teacup) as easily as cartoons and photorealistic people.

Ultra-low latency

LemonSlice delivers the quickest response time among major avatar providers, so conversations feel instant.

Create an avatar from one image

An interactive avatar starts from one photo. No training or fine-tuning required. Create unlimited interactive avatars with real-time outfit or setting changes.

Built for enterprise scale

Avatar sessions alongside ElevenLabs run at production scale.

Thousands of concurrent calls

Run thousands of avatar sessions side by side, built for high-volume production workloads.

Multi-region servers

Launch avatar sessions from the region closest to your users for lowest latency.

Zero data retention mode

Run avatar sessions that store no conversation data, built for privacy-sensitive enterprise workflows.

What builders ship with ElevenLabs + LemonSlice

Create avatars for everything from in-product customer support to lead qualification, corporate training, and language practice.

Customer support agent, in product

The avatar resolving a billing question inside a real support UI.

Lead qualification agent

Qualify inbound leads in a face-to-face website conversation.

Corporate training coach

Roleplay difficult conversations and train staff on policy.

Frequently asked questions

Stream the audio from ElevenLabs Agents or your Eleven voice pipeline to the LemonSlice avatar API. The rendered video streams back over WebRTC via LiveKit, Daily (Pipecat), or Agora, so users see a face responding in real time.
No. ElevenLabs runs the conversation and the voice, and LemonSlice renders the face. The two work side by side with a clean division of labor.
Yes. LemonSlice animates whatever audio you send it, so your Eleven voices, cloned or stock, sound exactly the same with a face attached.
Yes. LemonSlice accepts the audio stream from either lane, a full ElevenLabs Agents conversation or Eleven TTS running inside your own stack.
Yes. LemonSlice lip syncs to the audio itself rather than to a specific language, so any language your ElevenLabs voices speak renders with matching mouth movement and expression.
No. LemonSlice renders the interactive avatar in real time as the audio arrives, so conversations keep their natural back-and-forth pace.

Give your ElevenLabs agent a face

5-minute API setup. Your ElevenLabs stack stays untouched.