Avatar API for real-time, interactive video

LemonSlice animates any character from a single photo into a real-time avatar that listens, talks, and responds. Add the Avatar API to the stack you already use, or drop a hosted widget into your site with two lines of code.

  • Ultra-low latency
  • Unlimited custom avatars
  • 1000+ concurrency
  • 24-hr long calls
Get an API keyRead the docsQuickstart

From a single image to a live conversation

An avatar API lets your code create and animate a digital character. The LemonSlice Avatar API goes further and animates that character into a live, two-way conversation. Upload one photo, and go from image to a real-time video call with that character. No training, no fine-tuning, no video shoot.

Every avatar runs on a Character World Model, trained from scratch to listen, talk, and act in real time. It is a step past the deepfake and older generative technology behind traditional real-time avatars.

Illustrated character animated by the Avatar API
avatar = lemonslice.AvatarSession(
    agent_image_url="https://example.com/image.png",
    agent_prompt="Talk with hand gestures."
)

What you can build

Put a face on the agents you already run. Anywhere you have a chatbot or voice agent, add a talking, listening avatar the same day.

Sales and demos

Personalized product demos that respond to prospects 24/7

Customer support

On-brand AI assistant avatars that feel face-to-face

Learning and development

Immersive roleplay for sales, clinical, and manager training

Language learning

Always-available tutors with accurate lip sync

Physical installations

Interactive avatars for tourism offices, exhibits, and retail spaces

Entertainment

Interactive characters for games, stories, and companions

Any character. Any style.

LemonSlice is the only interactive avatar model that can animate non-humans, like a turtle or a smiling teacup, as easily as humans.

Update a character's appearance, emotions, and actions during a live session, and swap the source image in under a second.

Built for real-time

Speed and stability are the difference between a demo and production, so the Avatar API is tuned for live conversation.

Ultra-low latency

The fastest response time of any major avatar provider, at 471ms, about the blink of an eye. Read the technical report.

24-hour live calls

Sessions stay live for up to 24 hours without dropping, built for kiosks, installations, and always-on agents.

Live at 20 fps

Every frame is generated in real time from one photo, so replies feel like a real conversation, not a clip.

Thousands of concurrent calls

Run thousands of simultaneous avatar sessions — built for high-volume production workloads.

How interactive avatars work

LemonSlice adds a face layer on top of your voice agent. It works with any TTS and any LLM, so nothing in your stack has to change. Behind the scenes, speech-to-text and voice-activity detection listen, your LLM replies, text-to-speech generates audio, and LemonSlice turns that audio into real-time character video in a WebRTC call.

Step 1: Pick or upload any image.

Upload a photo of any character. No training, fine-tuning, or character rigs required. If it has a face, LemonSlice can animate it.

ElevenLabs v3
Sonnet 4
OpenAI Voice
Gemini Pro
Cartesia Sonic-3
GPT-5.5 Mini
Gemini Audio
Qwen3 235B
Hume

Step 2: Connect any LLM/voice model.

Plug in any language model, voice provider, and knowledge base through LemonSlice's API. OpenAI, Claude, ElevenLabs, Cartesia, and more.

Step 3: Go live with ultra-low latency.

Deploy to your site with a widget, hosted pipeline, or self-managed pipeline. LemonSlice runs at 471ms p99 latency, so conversations feel instant.

Set up an agent in 5 minutes with our developer-friendly API.

Get an API key, point LemonSlice at an image, and start a session. Call the REST endpoints to create, control, get, and list sessions, or clone the production-ready Next.js and LiveKit example to go from zero to a live avatar in an afternoon.

Get an API Key
Example projects
Read the docs
5 minute quickstart
Choose a code example
Quickstart RepoLivekit Docs
async def my_agent(ctx: agents.JobContext):

    avatar = lemonslice.AvatarSession(
        agent_image_url="https://lemonslice.com/image.png",
        agent_prompt="Talk with hand gestures.",
    )

    session = AgentSession(
        stt="deepgram/nova-2",
        llm="openai/gpt-5.3-chat-latest",
        tts="cartesia/sonic-3",
    )

    await avatar.start(session, room=ctx.room)
    await session.start(
    )

Models available for every use case

LemonSlice 2.1 is our state-of-the-art model. Available on all plans.

Get started
yourwebsite.com

LemonSlice Lite is our low-cost model for consumer interactive avatar apps

  • Low cost
  • Ultra-low latency
  • High volumes
  • Instant character creation
Request a demo

LemonSlice Pro is our high-res model for large-format displays and physical installations

  • High resolution
  • Physical installations
  • Exceptional visual quality
  • High-fidelity characters
Request a demo

Built for enterprise scale

Multi-region servers

Deploy avatar sessions from the region closest to your users for lowest latency.

Zero data retention mode

Run avatar sessions without storing conversation data — built for privacy-sensitive enterprise workflows.

Pricing

Plans start at $8/mo, and every plan includes API access. The base model runs about $0.16 per included minute. Bring your own LLM or voice model on any tier.

Learn more

Frequently asked questions

Interactive avatars are digital characters that engage in real-time conversations. They are a natural extension of voice agents. You can add one to your website or use the LemonSlice API to build avatars into your products. LemonSlice offers the best interactive avatars in the world - and the only ones that work for both photorealistic and cartoon characters.
It's easy to make a LemonSlice interactive avatar - all you need is an image. Get started in our playground or build with our API. Your image can be of any character in any style - from photorealistic humans to cartoon mascots. You can upload an image, generate one directly on LemonSlice, or pick one from the library.
Yes. LemonSlice interactive avatars are designed to reply instantly, creating natural, back-and-forth interactions just like a real conversation.
Yes, LemonSlice interactive avatars can speak in any language, allowing you to create engaging experiences for global audiences.
Yes. Our API allows you to create a real-time avatar from any LLM or AI Voice model.
Get started with LemonSlice interactive avatars for as little as $8 per month. For high-volume applications and enterprise support, reach out today. You get a certain number of credits each month with your subscription. Each minute of a call uses up credits that are deducted from the overall total. Turn on overage on your billing page to enable additional usage beyond what's included in your subscription.
We've trained our own proprietary video diffusion transformer model so that you can turn any character into an interactive avatar. If it has a face, LemonSlice can animate it. We support photorealistic humans, illustrated characters, stylized designs, cartoons, brand mascots, and more. Check out our avatar library for examples.
If you are a developer, you can use one of our plugins to integrate LemonSlice into your own agent pipeline. You send us audio, and we stream back video.
LemonSlice is for software developers and businesses building conversational AI experiences that need a face. If you have a voice agent or chatbot, LemonSlice adds the visual layer that makes interactions feel personal and engaging.
LemonSlice is versatile and widely applicable across industries. Anywhere you have a chatbot or voice agent, you can add an interactive avatar. Some specific use-cases include:
  • Learning & Development: Do corporate training with immersive AI roleplay conversations, like for sales training, clinician training, or manager training.
  • Language Learning: Practice conversation with patient, always-available tutors. LemonSlice has excellent lip sync, which is helpful for language learning.
  • Physical Installations: Deploy interactive avatars on kiosks, museum exhibits, and retail displays
  • Customer Support: Turn automated support into face-to-face conversations with an on-brand spokesperson. Real expressions and body language make customers feel heard.
  • Sales Enablement: Scale personalized product demos with interactive avatars that respond naturally to prospects. Available 24/7.
  • Entertainment: Build interactive characters for games, storytelling apps, and virtual companions. Natural reactions keep users engaged longer.
  • Hyper-realistic avatars: Generate photorealistic talking avatars from a single photo - indistinguishable from real video
  • Cartoon mascots: Bring brand characters and animated personas to life
  • Real-time interaction: Supports natural back-and-forth dialogue through voice and text
  • API: Simple integration into your existing voice agent or application stack
  • Scalable performance: Built to support large-scale, concurrent sessions with consistent quality
  • Low latency: Optimized infrastructure for some of the fastest avatar response times on the market
Yes, you can chat with several demo interactive avatars on our homepage for free. You can sign up for an account and make your own custom avatars. Or you can try our API integration and give your AI agents a face. If you'd like a demo, you can request one here.

The most expressive, interactive avatars. Built to connect.

Get startedContact sales