open-annieBrowser-based 3D character that combines spoken AI conversations with model-directed facial expressions and gestures.Apache-2.0
Browser-based 3D character that combines spoken AI conversations with model-directed facial expressions and gestures.
Talk with an animated 3D character in a browser, with speech delivered over WebRTC and a separate model selecting expressions and gestures from the conversation transcript. open-annie derives mouth animation from audio and also includes scripted preview and recorded replay modes. Live conversations use a Python broker, run locally or on fal, plus external model-service credentials.
open-annie official README · Reviewed 2026-10-13
- 01 / Feature noteTranscript-driven animation
A separate model chooses facial expressions and gestures from conversation text while speech travels to the browser over WebRTC.
Feature source ↗ - 02 / Feature noteScripted preview and replay
Browse a scripted character preview or replay a recorded conversation with its stored animation decisions.
Feature source ↗
GitHub stars
61
Detected license
Apache-2.0
Repository created
2026-10-07
Repository push
2026-10-07
2026-10-07Repository push
2026-10-07
GitHub stars
Unknown
i
Cached history uses a different month window; chart withheld until aligned.
Latest attempt: ok · Checked 2026-10-18T00:03:36.737302+00:00 · Last successful fetch 2026-10-18T00:03:36.737302+00:00 · Provider source
Hacker News stories
Unknown
i
OpenSSF Scorecard
Unknown
i
No result returned.
Checked 2026-10-27T12:07:11Z · Latest attempt: not found · Provider source
GitHub release
Unknown
i
No result returned.
Checked 2026-11-04T04:26:56Z · Latest attempt: not found · Provider source
Unknown
