Add a face to your Fish Audio voices

LemonSlice puts a lifelike, interactive AI avatar on top of Fish Audio's voice stack. Whether you run OpenAudio text to speech or your own cloned voices, the avatar turns that audio into natural, face-to-face conversation with your customers.

LemonSlice

At a glance

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

How the integration works

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

  1. Keep your Fish Audio setup

    Your Fish Audio TTS and cloned OpenAudio voices keep generating speech exactly as they do today. Nothing about your voice configuration changes.

  2. Stream the audio to LemonSlice

    Send the audio output from Fish Audio to the LemonSlice avatar API. The avatar renders the speech in real time with lip sync and expression.

  3. The avatar video streams to your users

    Video is delivered over WebRTC, natively via LiveKit, Daily (Pipecat), or Agora, so it drops into your existing real-time stack.

Add your interactive avatar in less than 5 minutes

A Fish Audio 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 Fish Audio 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....
    )

An interactive AI avatar that feels alive

Control actions and emotions

The Action Engine animates everything from the face to hands, shoulders, and posture. You control actions and emotions 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 able to animate non-humans (a smiling teacup, a turtle) as easily as photorealistic people and cartoons.

Ultra-low latency

LemonSlice offers the fastest responses of any major avatar provider, keeping conversations feeling instant.

Create an avatar from one image

A single photo is enough to create an interactive avatar. No training or fine-tuning required. Create unlimited custom characters with real-time outfit or setting changes.

Built for enterprise scale

Avatar sessions alongside Fish Audio run at production scale.

Thousands of concurrent calls

Run thousands of concurrent avatar sessions, designed for high-volume production workloads.

Multi-region servers

Choose the region closest to your users for avatar sessions to keep latency low.

Zero data retention mode

Run entirely without stored conversation data, designed for privacy-sensitive enterprise workflows.

What builders ship with Fish Audio + LemonSlice

Create avatars for everything from language practice to customer support, live streaming, and corporate training.

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 the audio from your Fish Audio TTS output to the LemonSlice avatar API. The interactive AI avatar lip syncs in real time and the video streams back over WebRTC.
No. Fish Audio generates the speech and LemonSlice renders the face that speaks it, so each product handles its own layer.
Yes. LemonSlice animates whatever audio you send, so your cloned OpenAudio voices work without modification.
All of them. LemonSlice is voice-agnostic and lip syncs any audio stream, including every OpenAudio voice and custom clone.
Yes. LemonSlice animates the audio itself rather than the text, so speech in any language Fish Audio generates lip syncs naturally.
No. LemonSlice renders the real-time avatar as the audio streams in, so conversations keep their natural pace.

Give your Fish Audio voices a face

5-minute API setup. Your voices stay exactly as they are.