Add a face to your Grok conversations

LemonSlice puts a lifelike, interactive avatar on top of xAI's Grok voice stack. Grok keeps handling the conversation and the realtime voice, and the real-time avatar turns that audio into natural, face-to-face conversation with your users.

LemonSlice

At a glance

Category
Realtime
Status
Compatible (works with any)
Type
Avatar API
Languages
Python, Node.js
Setup time
~5 minutes

How the integration works

xAI (Grok) keeps doing what it does today. LemonSlice turns the audio into a face.

  1. Keep your Grok setup

    Your xAI integration stays untouched. Grok keeps handling the conversation, the reasoning, and the realtime voice exactly as it does today.

  2. Stream the audio to LemonSlice

    Pipe the speech output from your Grok conversation into the LemonSlice avatar API. The avatar renders lip sync and expression in real time as Grok talks.

  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 live.

Drop in your real-time avatar with a short snippet

A xAI (Grok) 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 xAI (Grok), plus your STT and TTS, 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 drives the full performance across face, hands, shoulders, and posture. 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 is the one 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 responds faster than any other major avatar provider, so every exchange feels instant.

Create an avatar from one image

One photo creates a complete 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 xAI (Grok) run at production scale.

Thousands of concurrent calls

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

Multi-region servers

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

Zero data retention mode

Keep avatar sessions free of stored conversation data. Built for privacy-sensitive enterprise workflows.

What builders ship with xAI (Grok) + 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

Stream the speech from your Grok conversation into the LemonSlice avatar API. The interactive avatar renders lip sync and expression in real time, and the video streams back to your users over WebRTC.
No. Grok keeps handling the conversation and the voice while LemonSlice handles the face, rendering lip sync and expression on top of the audio Grok produces.
Yes. LemonSlice animates whatever audio you stream in, so the voice your users hear is still Grok's realtime voice, unchanged.
Any Grok setup that produces a speech stream works. If the conversation outputs audio, LemonSlice can give it a face.
No. LemonSlice is built for responsiveness, and the interactive avatar renders as the audio arrives, so every exchange still feels immediate and natural.
Yes. LemonSlice offers a zero data retention mode, so avatar sessions can run without storing any conversation data, designed for privacy-sensitive workflows.

Give your Grok conversations a face

5-minute API setup. Your xAI stack stays exactly as it is.