· 1 observation
Technical updates · 1
Package or technical metadata updated
View technical comparison →LemonSlice v1.0.0
Video avatar for voice agents
From the developer
Not specified in the available declarations: limitations, pricing & account requirements.
Add a LemonSlice video avatar to my LiveKit agent.
Developer declarations; not independently tested. Listing last checked Nov 12, 2026. Package observed Nov 11, 2026.
From the marketplace listing
LemonSlice turns any single image into a real-time, lip-synced video avatar that joins your LiveKit room as a participant. This plugin teaches ChatGPT and Codex to attach the avatar to an existing LiveKit agent in Python or Node.js, or to scaffold a complete app from the LemonSlice starter: API keys, the voice cascade, the ringing UI, and optionally CWM-1 so the character reacts and emotes during the call.
Language: English · Automatically detected from descriptions.
Exact text from the indicated source. A mention alone does not establish support for your task.
LemonSlice turns any single image into a real-time, lip-synced video avatar that joins your LiveKit room as a participant. This plugin teaches ChatGPT and Codex to attach the avatar to an existing LiveKit agent in Python or Node.js, or to scaffold a complete app from the LemonSlice starter: API keys, the voice cascade, the ringing UI, and optionally CWM-1 so the character reacts and emotes during the call.
Video avatar for voice agents
avatar livekit voice agent video lip sync lemonslice
Add a LemonSlice video avatar to a LiveKit voice agent, or build one from scratch.
· 1 observation
Package or technical metadata updated
View technical comparison →Find competitors to follow as you develop your plugin.
Build, test, and operate Phonic voice agents with product skills, API tools, and documentation search.
Shared terms: voice, agent, api, call
Create AI avatar videos, talking-photo videos, and cinematic AI videos with HeyGen. Generate or edit any AI image from a prompt or refere...
Shared terms: avatar, voice, video, single
Explore voice and multimodal agent ideas and build Pipecat agents with supported language and speech models, including speech-to-speech, ...
Shared terms: voice, agent, api, python
Synthflow lets you build and operate AI voice agents that make and take phone calls. This connector brings your Synthflow workspace into ...
Shared terms: voice, agent, api, call
Skills for building and testing voice AI agents with Vapi, including assistants, tools, calls, campaigns, squads, phone numbers, webhooks...
Shared terms: voice, agent, call
---
name: lemonslice-livekit-app
description: |
Add a LemonSlice video avatar to a LiveKit Agents app, or build one from scratch. LemonSlice turns any single image into a real-time, lip-synced talking avatar that joins the LiveKit room as a participant. Use when: (1) the user wants a talking avatar, a face on a voice agent, a lip-synced character, or a video agent on LiveKit — even if they do not name LemonSlice; (2) they mention lemonslice.AvatarSession, livekit-agents[lemonslice], @livekit/agents-plugin-lemonslice, or the lemonslice-examples repo; (3) they want the avatar to move and emote on its own or on cue (CWM-1, Character World Model, emotion engine, waving, smiling, laughing, leaning in), or to change its image or demeanor mid-call (update-image); (4) they are moving from another LiveKit avatar plugin (Tavus, HeyGen, Hedra, Beyond Presence, Anam, Synthesia); (5) the avatar never shows up, shows a black frame, drops after a fixed number of minutes, or the audio doubles. Works for Python and Node.js agents.
license: MIT
metadata:
author: lemonslice
version: "1.0.0"
---
# LemonSlice avatar on LiveKit
LemonSlice is an avatar plugin for LiveKit Agents, in Python and Node.js. You give it one image (any face, any art style, no training step) and it joins the room as a second participant that publishes lip-synced video. Your `AgentSession` keeps doing STT, LLM, and TTS; the plugin reroutes the session's audio to LemonSlice, which streams synced audio and video back into the room.
This skill works out what the user already has, picks one route, and implements it.
## Facts that shape every decision
- **Keys.** `LEMONSLICE_API_KEY` from https://lemonslice.com/developers, plus `LIVEKIT_URL`, `LIVEKIT_API_KEY`, `LIVEKIT_API_SECRET` from a LiveKit Cloud project. The LemonSlice key needs an active subscription; a key without one gets a `401`/`402` from the session API. Nothing runs without these, so confirm them before writing code.
- **Source image.** Exactly one of `agent_image_url` (public `https://` URL), `agent_image` (local file, uploaded by the plugin), or `agent_id` (an avatar saved in the LemonSlice dashboard). Default to `agent_image_url`; the dashboard is optional. Site paths like `/avatar.png` and `localhost` URLs fail because LemonSlice's servers fetch the image.
- **Both languages.** Python: `livekit-agents[lemonslice]`. Node: `@livekit/agents-plugin-lemonslice`. The frontend is just a LiveKit client.
- **Attach before start.** `await avatar.start(session, room)` must finish before `await session.start(...)`.
- **The avatar owns the audio.** Keep `audio_output=False` in `RoomOptions` (Python) or the equivalent in Node, and do not give the session another audio output afterwards. Otherwise the user hears the reply twice, or lip-sync dies.
- **Sessions time out.** Idle timeout defaults to 60 s and resets while the avatar talks (`idle_timeout`, `-1` disables). Hard cap is 30 minutes per session unless LemonSlice raises it.
- **Mid-call control is a REST call, not a plugin method.** Image and demeanor prompts change via `POST /api/liveai/sessions/{session_id}/control`. `avatar.start()` returns the `session_id` you need.
- **CWM-1 is the behavior model.** `model="cwm-1"` (or `"cwm-1-lite"`) switches the avatar to Character World Model 1, whose emotion engine decides what the character does and feels: waving, smiling, laughing, leaning in, glancing away. It can run fully automatically (`action_engine="natural"`) or take cues from your code. Under CWM-1, `agent_prompt` and `agent_idle_prompt` are ignored.
- **Plan-gated.** CWM-1 and `model="flash"` (fastest response) are on the Ultra and Enterprise tiers. Offer them; do not build on them until the user confirms their plan.
## Step 1: Find the starting point
Scan the codebase before asking anything.
| Look for | Where | Means |
| --- | --- | --- |
| `livekit-agents` / `livekit.agents` | `pyproject.toml`, imports | Python LiveKit agent → **Add** |
| `@livekit/agenPreview of the first 4,000 characters. Read full instructions →
Referenced files: 2 — file references are metadata, not package contents.
Initial release: LiveKit integration skill with CWM-1 and session control.
Declared in the saved package. Remote tools may change independently.
Publisher declarations from the archived package. These are separate from our research and the live service's terms.
Package observed Nov 11, 2026.
plugins_6ac05f3709e88191bb2bda6396a47aa1
Download plugin data (JSON)Plugin details: freshly prepared. Prepared . Refreshed when plugin data changes or after 6 hours. Your account and Follow status are live.