Add a face to your Hume agent

LemonSlice puts a lifelike, real-time avatar on top of Hume's empathic voice stack. Whether you run EVI speech-to-speech or Octave TTS voices, the real-time avatar turns that audio into natural, face-to-face conversation with your customers.

LemonSlice

At a glance

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

How the integration works

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

  1. Keep your Hume setup

    Your EVI configuration, Octave voices, prompts, and emotion handling stay exactly as they are. Hume keeps running the conversation and generating the speech.

  2. Stream the audio to LemonSlice

    Pipe the audio output from EVI or Octave TTS into a LemonSlice avatar session. The avatar renders in real time with accurate 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 realtime stack.

Add your avatar with one code block

A Hume 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 Hume 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....
    )

A real-time avatar that feels human

Control actions and emotions

The Action Engine animates the whole performance, 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 stands alone in animating non-humans, from a turtle to a smiling teacup, as easily as cartoons and photorealistic people.

Ultra-low latency

LemonSlice delivers the quickest response time among major avatar providers, so every exchange feels instant.

Create an avatar from one image

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

Built for enterprise scale

Avatar sessions alongside Hume run at production scale.

Thousands of concurrent calls

Run thousands of avatar sessions side by side. The platform is built for high-volume production workloads.

Multi-region servers

Launch avatar sessions from the region closest to your users, keeping latency as low as possible.

Zero data retention mode

Run avatar sessions that store no conversation data. Built for privacy-sensitive enterprise workflows.

What builders ship with Hume + LemonSlice

Create avatars for everything from wellness check-ins to interviewing, corporate training, and customer support.

Wellness check-in agent

A calm face for guided check-in conversations.

Interviewer

Structured screening interviews, face to face.

Corporate training coach

Roleplay difficult conversations and train staff on policy.

Frequently asked questions

Stream the audio output from EVI into the LemonSlice avatar API, and the real-time avatar renders with accurate lip sync as the speech arrives. Your EVI configuration stays untouched.
No. Hume handles the conversation, speech, and emotion understanding, while LemonSlice adds the visual layer, a live avatar that speaks with the audio Hume produces.
Yes. EVI keeps analyzing and responding to emotional cues exactly as before, and LemonSlice animates that expressive output as it streams in.
Yes. Any audio stream works, so you can pair the interactive avatar with EVI realtime speech-to-speech or with Octave TTS voices.
No. LemonSlice renders the avatar in real time as the audio streams in, so conversations keep the fast, natural pacing your Hume agent already delivers.
Yes. LemonSlice offers a zero data retention mode that runs sessions without storing any conversation data, built for privacy-sensitive enterprise workflows.

Give your Hume agent a face

Pair empathic voice with an expressive avatar in a 5-minute API setup.