Appgithub-com-pierrunoyt-personaplex-pinokio

PersonaPlex

v5.0

https://github.com/PierrunoYT/PersonaPlex-Pinokioupdated 1/28/2026, 5:34:58 PMindexed 1/28/2026, 5:35:11 PM

🗣️ PersonaPlex - NVIDIA's real-time speech-to-speech conversational AI model. Natural full-duplex conversations with customizable personas and voices. Requires powerful NVIDIA GPU (16-24GB VRAM), 32GB RAM, and Hugging Face account.

TypeApps

Community tagsLoading...

Check-in

Sort

Loading…

Check-ins (0)

View all

Platforms (0)

No reports yet.

Arch (0)

No reports yet.

GPU (0)

No reports yet.

RAM (0)

No reports yet.

VRAM (0)

No reports yet.

Recent commits

Updated start.js to simplify the server launch command by removing SSL support and adjusted the event monitoring regex to accommodate localhost connections.

PierrunoYT16 minutes agob210436

Refactored installation script to prioritize PyTorch installation before moshi, ensuring CUDA support is maintained. Updated moshi installation command to use uv pip with --no-deps to prevent dependency conflicts.

PierrunoYT1 hour ago3e247cb

Updated start.js to change the server launch command to use the moshi module with SSL support and refined the event monitoring regex for server URL output.

PierrunoYT1 hour ago2616e12

Updated installation script to include moshi package installation and improved completion notification with detailed instructions for Hugging Face model license acceptance and audio issue resolution.

PierrunoYT2 hours agoc33e637

Added user prompt for Hugging Face token in start.js to facilitate model downloading before launching the PersonaPlex server.

PierrunoYTyesterdayc10cf94

Initial Commit

PierrunoYTyesterdayab232d4