Back to browse
GitHub Repository
9 starsPython

Give your OpenClaw agent a face and voice with LiveKit and LemonSlice

by arbayi·Feb 21, 2026·5 points·0 comments

AI Analysis

MidCrowd PleaserEye Candy

Voice+video agent built by orchestrating Deepgram, ElevenLabs, LemonSlice, and LiveKit together.

Strengths
  • End-to-end 1-2s latency for full voice-to-video-response loop is respectable for real-time interaction.
  • LemonSlice lip sync quality exceeds author expectations, making avatar feel natural at scale.
Weaknesses
  • Orchestrates existing APIs and closed-source services; no novel architecture or competitive advantage over Talkbase, Dasha, or Vocode.
  • OpenClaw dependency limits generalizability; no clear path to swap in different agents without rewiring entire stack.
Category
Target Audience

AI agent developers building conversational interfaces with video components

Similar To

Talkbase · Vocode · Dasha

Post Description

For a fun side weekend project we gave our own OpenClaw agent called "Mahmut" a face and had a live interview with it. It went surprisingly well.

Here's a sneak peek from the interview: https://x.com/ptservlor/status/2024597444890128767

User speaks, Deepgram transcribes it, OpenClaw Gateway routes it to your agent, ElevenLabs turns the response into speech, and LemonSlice generates a lip synced avatar from the audio. Everything streams over LiveKit in real time.

Latency is about 1 to 2 seconds end to end depending on the LLM. The lip sync from LemonSlice honestly surprised us, it works way better than we expected.

The skill repo has a complete Python example, env setup, troubleshooting guide, and a Next.js frontend guide if you want to build your own web UI for it.

Similar Projects

AI/ML●●Solid

OpenClaw – An OS for AI agents that do work

The repo treats memory and identity as first-class, using SOUL.md/AGENTS.md/MEMORY.md plus per-day markdown logs so an agent can literally "read yesterday" before answering — a clear, human-readable model that avoids opaque vector stores. Useful CLI commands (init, doctor, grow, reflect) show the author thought about ergonomics and maintenance, but integration with LLM runtimes and evaluative evidence for the approach are light, so it's a pragmatic, opinionated toolkit rather than a breakthrough platform.

Niche GemBig Brain
mupengism
104mo ago
AI/ML●●Solid

OpenClaw-superpowers – Self-modifying skill library for OpenClaw agents

Self-modifying skills let agents persist new behaviors without restarts or config edits.

Ship ItBig Brain
Arkid
803mo ago