# photorealistic talking avatar with ARKit facial animation — Freysa Voice Lab

A photorealistic 3D head that talks — four facial meshes driven across 51 ARKit expression channels, speaking in a Microsoft neural voice, with a chat panel you can type into.

Type: project

Published: 2026-07-19

[Original page](<https://artlu.ai/project/photorealistic-talking-avatar-with-arkit-facial-animation-freysa-voice-lab>)

[Browse this group](<https://artlu.ai/ai/groups/other.md>)

Parent project: other builds

Recorded status: launched

Updated: 2026-09-16T16:05:14.761Z

Technologies: JavaScript, HTML, Three.js, ARKit blendshapes, Microsoft Azure TTS, ElevenLabs, GLM, VRM, matrix-js-sdk, Cloudflare Pages

## Details

**What is it?**
A face and a voice for an AI character that otherwise only existed as text. Two builds, one line of work: the first proved a 3D character could speak and lip-sync in a browser, the second replaced it with a photorealistic head and shipped it as a live interactive prototype.

**What it does**
- A photorealistic 3D head animated across 51 ARKit expression channels over four facial meshes
- Speaks in a Microsoft neural voice, with adjustable speech rate
- A chat panel — type to her, she answers and speaks the answer
- Keeps a memory of the conversation, and a separate history view
- Camera position is adjustable and resettable
- Ships as an embed script that drops into any page

**How it works**
The earlier build lip-synced a stylized VRM character by reading the energy of the generated audio through a viseme map — no phoneme timeline, so it worked with any voice provider. The current build replaces that with real ARKit blendshape channels, which is what lets a photorealistic face hold an expression rather than just open and close a mouth. It carries a genuine test suite: voice settings, speech rate, emotions, token handling, and memory are each covered, because it was built to be embedded somewhere other than the page it was written on.

**Built with**
JavaScript and HTML, Three.js, ARKit blendshapes, Microsoft Azure neural TTS with an ElevenLabs adapter, GLM for the replies, deployed on Cloudflare Pages.

## Links

[Site or demo](<https://freysa-avatar-test.pages.dev/>)


Status and dates describe the published record, not a recent test of an external service. Missing details are not inferred. Public links do not imply an open-source licence or permission to reuse material.

[Directory](<https://artlu.ai/llms.txt>)