Add a face to your Gemini agent

LemonSlice puts a lifelike, interactive AI avatar on top of Gemini's voice stack. Whether you run Gemini Live, TTS, or STT, the real-time avatar turns that audio into natural, face-to-face conversation with your customers.

LemonSlice

At a glance

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

How the integration works

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

  1. Keep your Gemini setup as is

    Your Gemini Live session, prompts, voices, and any TTS or STT configuration stay exactly where they are. Gemini keeps producing the conversation audio.

  2. Stream the audio to LemonSlice

    Pipe Gemini's audio output into the LemonSlice avatar API. The avatar renders in real time with accurate lip sync and expression.

  3. The avatar video streams to your users

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

Ship your interactive avatar with simple code

A Gemini Realtime 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 Gemini for TTS and STT, plus your 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....
    )

A lifelike avatar in every conversation

Control actions and emotions

Face, hands, shoulders, and posture all move through the Action Engine. You control actions and emotions through the API, down to a prompt like "talk with hand gestures."

Works with any character, in any style

LemonSlice is the only interactive avatar model that handles non-humans (a smiling teacup, a turtle) as easily as photorealistic people and cartoons.

Ultra-low latency

LemonSlice delivers the fastest response time of any major avatar provider, keeping conversations feeling instant.

Create an avatar from one image

Any photo becomes an interactive avatar. No training or fine-tuning required. Create unlimited custom characters with real-time outfit or setting changes.

Built for enterprise scale

Avatar sessions alongside Gemini Realtime run at production scale.

Thousands of concurrent calls

Run avatar sessions by the thousands at once, designed for high-volume production workloads.

Multi-region servers

Serve avatar sessions from the region nearest your users to keep latency low.

Zero data retention mode

Run sessions with zero stored conversation data, designed for privacy-sensitive enterprise workflows.

What builders ship with Gemini + LemonSlice

Create avatars for everything from kids tutoring to interviewing, corporate training, and language practice.

Kids tutor

A patient tutor that answers every why.

Interviewer

Structured screening interviews, face to face.

Corporate training coach

Roleplay difficult conversations and train staff on policy.

Frequently asked questions

Keep your Gemini setup unchanged and stream its audio output to the LemonSlice avatar API. The interactive AI avatar renders in real time and the video streams to your users over WebRTC.
No. Gemini handles reasoning, speech, and conversation, while LemonSlice renders the interactive AI avatar layer on top.
Yes. LemonSlice animates whatever audio Gemini produces, so your chosen Gemini voice carries through unchanged.
Yes. Whether you use Gemini's realtime live audio or combine its TTS and STT options in your own pipeline, the audio streams into LemonSlice the same way.
LemonSlice animates the audio your Gemini agent produces, so any language Gemini speaks works. Lip sync follows the audio itself rather than a fixed language list.
No. LemonSlice is built for real-time conversation and delivers the fastest response time of any major avatar provider. Conversations still feel instant.

Give your Gemini agent a face

5-minute API setup. Your Gemini pipeline stays exactly as it is.