Add a face to your Vapi agent

LemonSlice puts a lifelike, real-time avatar on top of your Vapi voice agents. Whether you run phone assistants, web calls, or Vapi workflows, the real-time avatar turns that audio into natural, face-to-face conversation with your customers.

LemonSlice

At a glance

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

How the integration works

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

  1. Keep your Vapi agent as is

    Your Vapi assistant keeps handling the conversation, transcription, reasoning, tool calls, and voice output. No changes to your prompts, workflows, or phone and web deployments.

  2. Stream the audio to LemonSlice

    Pipe the audio output from your Vapi agent into a LemonSlice avatar session. LemonSlice renders lip sync and expression in real time as the audio 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 web client.

Drop in your real-time avatar with a short snippet

A Vapi 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(
        # Connect your Vapi agent audio, then start the avatar 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 moves face, hands, shoulders, and posture together. 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 avatar model that brings non-humans to life (a turtle, a smiling teacup) as easily as cartoons and photorealistic people.

Ultra-low latency

LemonSlice leads every major avatar provider on response time, so conversations feel instant.

Create an avatar from one image

Turn any image into an interactive avatar. No training or fine-tuning required. Create unlimited interactive avatars with real-time outfit or setting changes.

Built for enterprise scale

Avatar sessions alongside Vapi run at production scale.

Thousands of concurrent calls

Scale avatar sessions into the thousands, built for high-volume production workloads.

Multi-region servers

Place avatar sessions in the region nearest your users for lowest latency.

Zero data retention mode

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

What builders ship with Vapi + 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 Vapi assistant unchanged and stream its audio output to the LemonSlice avatar API. The real-time avatar renders as the audio arrives and streams back to your users over WebRTC.
No. Vapi keeps running the conversation, including transcription, reasoning, and voice output. LemonSlice is the face layer that renders that conversation as a live avatar.
Yes. LemonSlice animates whatever audio your Vapi agent produces, so your chosen voice carries through unchanged.
The avatar renders wherever video can display, so web deployments are the natural fit. Phone calls stay audio-only, and the same agent can serve both channels.
Any Vapi configuration that produces an audio stream works, including assistants, workflows, and web deployments. Your prompts, tools, and call logic stay exactly where they are.
Yes. LemonSlice animates the audio itself rather than the underlying text, so any language your Vapi agent speaks carries through with natural lip sync.

Give your Vapi agent a face

Keep your Vapi setup. Add a live avatar with a 5-minute API setup.