Add a face to your Simplismart models

LemonSlice puts a lifelike, real-time avatar on top of the models you serve on Simplismart. Whether you run Whisper-class STT, custom TTS, or LLMs, the real-time avatar turns that audio into natural, face-to-face conversation with your customers.

LemonSlice

At a glance

Categories
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

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

  1. Keep your Simplismart deployments as they are

    Your STT, TTS, and LLM endpoints served on Simplismart keep handling the conversation. No redeploys, no config changes, no new serving stack.

  2. Stream the audio to LemonSlice

    Send the audio output from your Simplismart-served TTS model to the LemonSlice avatar API. The avatar renders in real time with lip sync and natural 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 transport.

Ship your interactive avatar with simple code

A Simplismart 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 Simplismart 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

The Action Engine brings face, hands, shoulders, and posture to life. You direct actions and emotions straight from the API, down to a prompt like "talk with hand gestures."

Works with any character, in any style

LemonSlice remains the only interactive avatar model that animates non-humans, from a turtle to a smiling teacup, as easily as cartoons and photorealistic people.

Ultra-low latency

LemonSlice outpaces every major avatar provider on response time, so every exchange feels instant.

Create an avatar from one image

Any image turns into a working interactive avatar. No training or rigging required. Build unlimited custom characters with real-time outfit or setting changes.

Built for enterprise scale

Avatar sessions alongside Simplismart run at production scale.

Thousands of concurrent calls

Handle thousands of simultaneous avatar sessions. The platform is built for high-volume production workloads.

Multi-region servers

Host avatar sessions in the region closest to your users, keeping latency as low as possible.

Zero data retention mode

Run avatar sessions with no conversation data retained. Built for privacy-sensitive enterprise workflows.

What builders ship with Simplismart + LemonSlice

Create avatars for everything from customer support to companion apps, live streaming, and corporate training.

Customer support agent

Answer, triage, and resolve customer questions face to face.

High-volume consumer app

Low-cost avatar sessions at consumer-app scale.

Streaming host

A live host that reads and responds to chat.

Frequently asked questions

Keep your models serving on Simplismart and stream the TTS audio output to the LemonSlice avatar API. The avatar video streams back over WebRTC via LiveKit, Daily with Pipecat, or Agora.
No. Simplismart serves your speech and language models, and LemonSlice renders the real-time avatar that speaks the audio those models produce.
Yes. Any TTS model you deploy on Simplismart streams into LemonSlice exactly like a hosted voice API, so your voices stay exactly as you tuned them.
No. Your Whisper-class STT and LLM endpoints keep handling transcription and conversation logic, and only the final audio routes to the real-time avatar.
LemonSlice animates the avatar from the TTS audio your pipeline produces, so any TTS model you serve on Simplismart works. Your STT and LLM deployments keep their roles upstream without changes.
Yes. The real-time avatar lip syncs to whatever audio your Simplismart-served TTS model produces, so every language and voice your model supports carries straight through.

Give your Simplismart models a face

5-minute API setup. Your serving stack stays exactly the same.