ChorusFace — Talking Face Companion
Your AI talks into a blank UI. ChorusFace lip-syncs a photoreal TickFeed face and streams MJPEG for embed — host keeps LLM + TTS. Beta dogfood; self-host...
Host owns LLM + TTS · MJPEG embed · beta one avatar · isolated landing demo.
Open /products/chorusface.html → try the live demo band → self-host from GitHub when ready.
Your AI already talks. Visitors still stare at a blank box.
ChorusFace is the talking-face companion for your product. You keep the LLM and TTS; we lip-sync a photoreal TickFeed avatar and stream MJPEG you can embed with an image tag — without shipping a WebGL face stack.
Brain + voice stay yours
Conversation and audio remain in your host app. ChorusFace owns the face.
Face follows speech
Cue mouth motion via speak; preferred path streams host PCM to /voice/*.
Embed, don’t rebuild
Self-host from GitHub / Docker. One fixed avatar in this beta — no fake PyPI.
Why a face layer
Voice without a face
Your agent already talks. Visitors still stare at a blank box. ChorusFace adds a photoreal talking face without taking over your LLM or TTS.
WebGL rewrites are heavy
Shipping a full browser avatar stack is a product of its own. ChorusFace streams a ready TickFeed face as MJPEG so you embed with an image tag.
Lease fights across surfaces
One API key leases one client_id. This landing demo uses a dedicated lease so homepage hub chat never shares the face connection.
How it fits
1. Host LLM replies
Your product (or this landing demo chat) generates text. ChorusFace never owns the conversation.
2. Host TTS speaks
Browser Web Speech or your server voice plays audio. Face cue never mutes host audio.
3. ChorusFace lip-syncs
Server cues /prism/speak (or streams host PCM to /voice/*). MJPEG shows the talking face.
What ships in this beta
Host owns brain + voice
Your app keeps the LLM and TTS. ChorusFace lip-syncs the avatar and streams the face. Preferred path: host PCM → /voice/*; beta demo cues mouth via /prism/speak.
MJPEG embed
GET /stream.mjpg (token + client_id). This site proxies the landing demo at /api/agents/chorusface-demo/stream so HTTPS pages never load http://127.0.0.1.
Beta one avatar
0.2.0b1 ships one fixed TickFeed avatar. Not a multi-identity picker. Not a chatbot product. Not default TTS.
Neural World Runtime (NWR)
Vendored NWR substrate — field/cell world → continuous face motion from speech/behavior. Deep contracts stay in the ChorusFace design docs — not marketing claims on this page.
Speech → biomechanics → field
Visemes and mouth poses drive muscle, jaw, gaze, and breathing signals; those become field impulses the runtime ticks into a deforming face.
You embed the stream
Integrators cue speak/voice and consume MJPEG — you do not ship a full WebGL face stack in the browser.
Honest beta boundary
This page does not claim bit-identical replay or Master Lock as proven shipping guarantees. Deep NWR contracts stay in the ChorusFace / NWR design docs while dogfood continues.
- Neural World Runtime (NWR) — Vendored field/cell substrate that ticks continuous face motion.
- TickFeed — Fixed calibrated avatar world for this beta (one identity).
- Visemes & mouth poses — Speech cues mapped to mouth shapes before muscle drive.
- Biomechanics — Muscle, jaw, gaze, and breathing signals from those cues.
- Field impulses · cell drives — Biomechanics become field commands the runtime applies each tick.
- Host-voice lip-lock — Preferred path: host PCM → /voice/* so the face follows your TTS.
- FaceBridge — HTTP control surface for speak, voice, status, and stream.
- MJPEG embed — Authenticated /stream.mjpg for web UIs — no browser WebGL face stack.
Design docs (not marketing claims): Architecture.md (not a marketing claim) · NWRDataDesign.md (not a marketing claim)
When not
Not a chatbot
Conversation and tools stay in your host agent.
Not default TTS
Audio is host-owned; face follows.
Not multi-avatar
This beta has one TickFeed identity.
Need an API key?
FaceBridge leases require an API key tied to your client_id. Email info@insightits.com to request a key so you can test and embed ChorusFace in your product. Say whether you need a short dogfood test or a longer embed trial.
Email: info@insightits.com
Capabilities
Host owns brain + voice
Your product keeps the LLM and TTS. ChorusFace lip-syncs the avatar and streams the face.
MJPEG embed
Stream /stream.mjpg for web embed. This landing proxies same-origin so HTTPS never loads http://127.0.0.1.
Beta one avatar
0.2.0b1 ships one fixed TickFeed avatar. Not a chatbot, not default TTS, not a multi-identity picker.
Published evidence
ChorusFace product beta contract. Host owns LLM + TTS; ChorusFace is face-only. Beta 0.2.0b1 one TickFeed avatar. See ProductBeta.md / FaceServiceEmbed.md.
Install
Self-host from GitHub / Docker (no PyPI on this page). Need an API key to test or embed? Email info@insightits.com. Soft CTA: try the landing demo. Docs: ProductBeta.md · FaceServiceEmbed.md.
Pricing
ChorusFace beta dogfood — open source on GitHub (no PyPI package on this page). Self-host from https://github.com/insightitsGit/ChorusFace. Need an API key for test/embed? Email info@insightits.com. Soft CTA: try the live demo on this landing.
Frequently asked questions
What is ChorusFace?
Your AI already talks — visitors still stare at a blank box. ChorusFace is the talking-face companion: your app keeps the LLM and TTS; we lip-sync a photoreal TickFeed avatar and stream MJPEG for embed. Beta 0.2.0b1. Landing: https://www.insightits.com/products/chorusface.html
Is ChorusFace a chatbot?
No. ChorusFace is the face layer only. The host product owns the LLM conversation and TTS audio. This landing demo chat is a scoped explainer so you can see the face move — not a replacement for the InsightITS Website Hub.
Does ChorusFace replace my TTS?
No. Host TTS stays on. ChorusFace cues mouth motion (via /prism/speak now; host PCM → /voice/* preferred later). Do not mute host audio when the face is queued.
Can I pick different avatars?
Not in this beta. One fixed TickFeed avatar. Multi-identity picker is out of scope for 0.2.0b1.
Is there a PyPI package?
No fake PyPI for this page. Self-host from GitHub / Docker: https://github.com/insightitsGit/ChorusFace
What happens if the face service is down?
Demo chat still returns text. Face stream may show offline. Homepage AI chat is unrelated and stays on its own path.
How do I embed the face in my product?
Run the ChorusFace container, lease a client_id with your API key, then <img> the MJPEG stream (or same-origin proxy). See docs/FaceServiceEmbed.md and docs/ProductBeta.md in the ChorusFace repo. Need a key? Email info@insightits.com and ask for a ChorusFace API key to test and embed.
How do I get an API key to test or embed?
Email info@insightits.com with subject “ChorusFace API key request (test & embed)”. Include your name, company/product, and whether you need a short dogfood test or an embed trial. We issue a FaceBridge API key tied to a client_id — do not share keys in public issues or git.
What is NWR (Neural World Runtime)?
NWR is the vendored substrate under the TickFeed avatar: a field/cell world that turns speech and behavior signals into continuous face motion. ChorusFace exposes speak/voice + MJPEG embed — not a browser WebGL face stack. Deep contracts live in docs/Architecture.md and docs/NWRDataDesign.md on GitHub.
Is deterministic replay / Master Lock proven?
Do not treat those as shipping marketing claims on this beta page. Dogfood the face companion first; authority claims stay parked until accepted.
Official package links: ChorusFace source code on GitHub · ChorusFace interactive demo