fikrikarim /
parlor
On-device, real-time multimodal AI with features similar to GPT-Live
Updated 36 min ago
+7 stars gained this week
Stars gained each day, last 30 days
Usual pace · 1 / day
Oct 4Oct 19Today
This week Before Usual pace
In short
A research-preview voice AI that runs entirely on-device, using a real-time cascade of speech recognition, a Gemma model, and text-to-speech. Built for people who want a private, local alternative to cloud voice assistants, such as English learners.
Summary written by AI from the repository’s description and README.
fikrikarim / parlor
View on GitHub(opens in new tab)