Add a face to your Cartesia voices

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

LemonSlice

At a glance

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

How the integration works

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

  1. Keep your Cartesia setup

    Your Sonic voices, Ink transcription, and Line agents keep running unchanged. LemonSlice sits downstream of the audio Cartesia produces, so no pipeline rework is needed.

  2. Stream the audio to LemonSlice

    Send Cartesia's streaming audio output to the LemonSlice avatar API. The avatar renders in real time with accurate lip sync and expression as each chunk arrives.

  3. The avatar video streams to your users

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

Add your interactive avatar with a few lines of code

A Cartesia 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 Cartesia 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....
    )

An interactive avatar that feels human

Control actions and emotions

The Action Engine handles the physical performance, from the face to 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 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 quickest response time among major avatar providers, keeping conversations feeling instant.

Create an avatar from one image

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

Built for enterprise scale

Avatar sessions alongside Cartesia run at production scale.

Thousands of concurrent calls

Scale to thousands of simultaneous avatar sessions, designed for high-volume production workloads.

Multi-region servers

Sessions run from the region closest to your users to keep latency at its lowest.

Zero data retention mode

Store no conversation data during sessions, designed for privacy-sensitive enterprise workflows.

What builders ship with Cartesia + LemonSlice

Create avatars for everything from language practice to customer support, live streaming, and airport kiosks.

Language practice partner

Practice real conversations in another language.

Customer support agent

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

Streaming host

A live host that reads and responds to chat.

Frequently asked questions

Stream Cartesia's audio output to the LemonSlice avatar API and the avatar speaks it in real time, with video delivered back over WebRTC via LiveKit, Daily (Pipecat), or Agora.
No. Cartesia handles the voice side, speech synthesis, transcription, and agent logic, while LemonSlice renders the real-time avatar video on top.
Yes. LemonSlice animates whatever audio Cartesia streams, so your Sonic voice selection and settings carry over untouched.
Yes. Any Cartesia product that outputs streaming audio, including Line agents and standalone Sonic TTS, can feed the LemonSlice avatar API.
All of them. Sonic text to speech, Ink speech to text, and Line voice agents each slot into the pipeline, and the avatar renders whichever audio reaches it.
No. Cartesia streams audio exactly as before, and LemonSlice renders the avatar in parallel with ultra-low latency, so the conversation stays real time.

Give your Cartesia agent a face

Keep your voices and pipeline, add a real-time avatar with a 5-minute API setup.