Add an interactive avatar to any voice stack
LemonSlice is the face layer for voice agents. It works with any voice agent platform, any LLM or realtime model, and any TTS or STT provider, and ships live WebRTC integrations with LiveKit, Daily (Pipecat), and Agora. Your stack handles the conversation; LemonSlice streams the avatar.
Browse integrations
Every provider LemonSlice works with, in one directory. Pick a layer of the stack to see its integrations.
LemonSlice works with any voice agent platform. If your agent produces an audio stream, we can put a face on it.
Vapi
Vapi handles the voice conversation while a LemonSlice real-time avatar gives it a lifelike face.
Retell
Retell runs the phone conversation, LemonSlice renders a real-time face with lip sync and expression on top.
Bland
Bland phone agents gain a real-time interactive avatar, turning every call into a face-to-face conversation.
ElevenLabs
ElevenLabs runs the voice, LemonSlice renders the interactive avatar your users actually see and talk to.
Cartesia
Stream Cartesia's low-latency TTS into the avatar for fully real-time conversations.
InWorld
Inworld characters get a lifelike real-time avatar, turning their voices into live face-to-face conversation.
Smallest AI
Pair Smallest AI's Lightning voices and Atoms agents with a real-time LemonSlice avatar for face-to-face conversations.
Speechmatics
Speechmatics multilingual speech-to-text and Flow agents paired with a real-time LemonSlice avatar your users can see.
Don't see your provider?
If it streams audio, it works with LemonSlice. The avatar API accepts any audio source and returns a real-time video stream. No named integration required.
Your agent talks.
LemonSlice gives it a face.
LemonSlice sits on top of the voice pipeline, not inside it. Nothing about your existing agent changes.
Step 1: Keep your voice agent
Your platform keeps handling speech-to-text, the LLM, and text-to-speech exactly as it does today.
Step 2: Stream audio to LemonSlice
Pipe your agent's audio output to the LemonSlice API. The avatar renders speech, expression, and lip sync in real time.
Step 3: Embed the video stream
The avatar streams back over WebRTC into your app or site, natively through LiveKit, Daily (Pipecat), or Agora.
Frequently asked questions
Put a face on your voice agent
5-minute API setup. Works with the stack you already have.





















