---
title: "face-to-face"
description: "Face to face: talk to your agent and watch it answer: a full-screen halftone face that lip-syncs to the real audio, captions every word as it is spoken, and a small living orb that opens it from the Chat space. Where the"
canonical: https://agentpluginsdirectory.com/plugins/face-to-face
last-updated: 2026-10-05
---

# face-to-face
Face to face: talk to your agent and watch it answer: a full-screen halftone face that lip-syncs to the real audio, captions every word as it is spoken, and a small living orb that opens it from the Chat space. Where the engine offers it, Talk live puts a realtime voice on the same face: it chats with you and hands the work to your agent.
- Slug: face-to-face
- Publisher: Dimension
- Repository: https://github.com/insodimension/dimension-community
- Manifest: packs/face-to-face/plugin.json
- Version: 0.1.3
- License: MIT
- Category (editorial): other
- Skills: 0
- MCP servers: 0
- Stars: 1
- Repository created: 2026-07-31
- Repository last pushed: 2026-10-05
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/face-to-face
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What face-to-face does, in the publisher's words

Talk to your agent and watch it answer. A full-screen surface for the Chat space: a halftone dot-matrix head that turns, blinks and lip-syncs to the actual spoken audio, captions every word as it is said, and a small living orb that opens it.

One bundle, two components (plugin.json):

A space opts in with workspace.surfaces: [..., "face"], workspace.chrome.face: "none", components.face: "face-to-face", the pinned door, a rail action { target: "surface", surface: "face" }, and requires.plugins: ["face-to-face"] (the Chat space's packs/chat/plugin.json is the wiring proof).

- src/index.tsx: the two components; the only wiring to the host.
- src/surface/: the surface: surface-model.ts (pure: phase to screen, Back/Esc), face-surface.tsx, face-door.tsx, orb.ts (the door's dots), waveform*.ts(x), voice.ts and live.ts (hook adapters), live-mouth.ts (how a call moves the mouth), head*.ts (asset), styles.ts.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/insodimension/dimension-community/HEAD/packs/face-to-face/README.md