lemonslice.com valid

LemonSlice

LemonSlice is an AI research lab that built the world’s first Character World Model — interactive characters that talk, listen, and react in real time. Use the LemonSlice API to embed lip-synced avatar video in your product or website over WebRTC.

For agents: AI research lab offering the LemonSlice API and widget for embedding real-time, lip-synced talking avatar video over WebRTC, with developer docs and quickstart.

ai avatarslip-sync videowebrtcreal-time characterscharacter world model

Their llms.txt

The beginning of the file, from our validated copy saved 2026-10-21T05:40:55.470Z. Cached copy · Source on lemonslice.com

# LemonSlice

> LemonSlice is an AI research lab that built the world’s first Character World Model — interactive characters that talk, listen, and react in real time. Use the LemonSlice API to embed lip-synced avatar video in your product or website over WebRTC.
> Try it out at [lemonslice.com](https://lemonslice.com). Get your API key from the [LemonSlice developers page](https://lemonslice.com/developers) to start building.

Character World Models go beyond traditional real-time avatars based on deepfake or older generative tech. Create any character from a single image (no training or fine-tuning) and go from image to live video call instantly.

Highlights:
- Ultra-low latency ([benchmarks](https://lemonslice.com/blog/lemonslice-flash)), 1000+ concurrency, multi-hour calls
- Instant avatar creation from 1 photo; 5-minute API setup
- Model capabilities: hand gestures, emotions, holding objects, clothing swaps, physics/spatial modeling, full-body movement, photorealism, and non-human/cartoon characters
- In-call control: update appearance, emotions, and actions during a live session

How a call works: STT/VAD listens → LLM decides the reply → TTS produces audio → LemonSlice turns that audio into real-time character video in a live WebRTC call. LemonSlice is the graphics / “face” layer on top of any TTS and LLM; latency depends heavily on your upstream STT/LLM/TTS.

API inputs: (1) image for appearance, (2) streaming TTS audio for speech, (3) optional Action Engine for gestures/actions (Enterprise).

Primary path: API integration via LiveKit, Daily/Pipecat, Agora, or a direct WebSocket — you keep STT/LLM/TTS and call UI; LemonSlice adds avatar video. Also available: no-code [Widget](https://lemonslice.com/docs/widget/overview.md) and low-code [Hosted Pipeline](https://lemonslice.com/docs/hosted/overview.md) (LemonSlice manages speech/intelligence).

## Reference

- [Overview](https://lemonslice.com/docs/introduction/index.md): Product + Character World Model overview, capabilities, how it works, and integration options
- [Quickstart (5 min)](https://lemonslice.com/docs/introduction/quickstart.md): Clone a production-ready Next.js + LiveKit agent locally — the recommended starting point
- [Production checklist](https://lemonslice.com/docs/reference/production-checklist.md): Call lifecycle, latency, interruption handling, and production deployment tips
- [LiveKit Integration](https://lemonslice.com/docs/livekit/index.md): Add LemonSlice avatars to a LiveKit Agents pipeline
- [Pipecat Integration](https://lemonslice.com/docs/pipecat/index.md): Add LemonSlice avatars to a Pipecat agent
- [Agora Integration](https://lemonslice.com/docs/agora/index.md): Add LemonSlice avatars to Agora Conversational AI Engine
- [WebSocket Integration](https://lemonslice.com/docs/websocket/index.md): Drive a LemonSlice avatar from your own audio stack over WebSocket
- [Avatar Image Tips](https://lemonslice.com/docs/prompting-guide/avatar-image-tips.md): Reference image
…

Related sites

Other listed sites in AI and machine learning. See the whole category →

Machine-readable: GET /v1/resolve?q=lemonslice.com · GET /v1/domain/lemonslice.com · this page as Accept: application/json or text/markdown · MCP lookup_domain

Automatically discovered from public files. Inclusion does not imply endorsement or publisher participation.

Claim my listing on Agent Web Map for lemonslice.com:
1. POST https://agentwebmap.com/v1/sites/lemonslice.com/claims and keep claim_id and claim_secret private.
2. Publish the proof: add the line "AgentWebMap ownership: <token>" (token from step 1) to https://lemonslice.com/llms.txt, or use the DNS, meta-tag or well-known method the response describes.
3. POST https://agentwebmap.com/v1/sites/lemonslice.com/verify with {"claim_id": "...", "claim_secret": "..."}.
4. Save the api_key from the answer; it manages the listing (PATCH https://agentwebmap.com/v1/sites/lemonslice.com).
MCP equivalent: tools begin_ownership_claim, then verify_domain, at https://agentwebmap.com/mcp. Docs: https://agentwebmap.com/docs#verify

Corrections or removal requests: contact the directory.