Add a face to your Smallest AI agent

LemonSlice puts a lifelike interactive AI avatar on top of Smallest AI's voice stack. Whether you run Lightning TTS voices or Atoms agents, the 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

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

  1. Keep your Smallest AI setup

    Your Atoms agents and Lightning voices keep running as they do today. No changes to your prompts, voice configuration, or call logic.

  2. Stream the audio to LemonSlice

    Pipe the audio output from Smallest AI into a LemonSlice avatar session through the API. The avatar renders speech in real time with lip sync and expression.

  3. The avatar video streams to your users

    LemonSlice delivers the avatar video over WebRTC, natively via LiveKit, Daily (Pipecat), or Agora, so it drops into your existing real-time stack.

Add an interactive AI avatar in minutes

A Smallest AI 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 Smallest AI 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 face, hands, shoulders, and posture. You trigger actions and emotions from 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 animates non-humans, a turtle or a smiling teacup, with the same ease as cartoons and photorealistic people.

Ultra-low latency

LemonSlice has the fastest response time of any major avatar provider, so replies feel instant.

Create an avatar from one image

From one photo comes a full interactive avatar. No training or fine-tuning needed. Make unlimited custom characters and change outfits or settings in real time.

Built for enterprise scale

Avatar sessions alongside Smallest AI run at production scale.

Thousands of concurrent calls

Run thousands of simultaneous avatar sessions, ready for high-volume production workloads.

Multi-region servers

Deploy avatar sessions from the region closest to your users so latency stays minimal.

Zero data retention mode

Run avatar sessions without storing conversation data, made for privacy-sensitive enterprise workflows.

What builders ship with Smallest AI + 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

Keep your Atoms agent or Lightning pipeline as it is, then stream its audio output to the LemonSlice avatar API. The rendered avatar video streams back to your users over WebRTC.
No. Smallest AI handles the voice and conversation side, and LemonSlice handles the face, with real-time avatar rendering, lip sync, and expression.
Yes. LemonSlice animates whatever audio you send it, so every Lightning voice you use today works unchanged.
Yes. Any audio stream works, whether it comes from raw Lightning TTS output or a full Atoms voice agent.
Yes. LemonSlice lip-syncs to the audio itself, so the interactive AI avatar animates any language your Lightning voices or Atoms agents speak.
No. LemonSlice renders the avatar as the audio streams in, so conversations keep their natural back-and-forth rhythm.

Give your Smallest AI agent a face

Bring an interactive avatar to your voice stack with a 5-minute API setup.