NVIDIA/personaplex

★11,740Python🇺🇸 North AmericaMIT⑂ 1,598Issue 38Updated Mar 3, 2026

PersonaPlex code.

Full-duplex speech model lets you script persona and voice — PersonaPlex is NVIDIA's real-time, full-duplex speech-to-speech model built on the Moshi architecture. It adds persona control via text role prompts and audio-based voice conditioning, letting developers shape a consistent character for low-latency spoken dialogue. Ships with weights and a web UI server.

LLMs & ML

Metrics

Relative growth (7d)+4%Growth over the last 7 days relative to size

Acceleration+621%Change in growth pace from the week before

Attention76The three metrics scaled to 0–100 and combined

Retention can be computed 30 days after a repository first trends (it isn't shown until then). See About for how each metric is defined.

Star growth and Trending appearances (last 30 days)

First listed+311★/dayDailyWeekly

Sep 30, 2026Oct 29, 2026

Bands mark days on the trending list (darker = higher rank)

Daily trending ranks as a table (2 days)

Date	Daily	Weekly
Oct 20, 2026	—	python #12 +270
Oct 14, 2026	python #11 +148	—

Created Jan 6, 2026 · First on trending Oct 14, 2026

Other notable repositories in the same category (LLMs & ML)

pst2154/nemotron-deciffusionStructured decisions from an 8B diffusion model in a single GPU pass
todesking/slopsamplerCataloging the telltale phrases of AI-generated Japanese text
datalab-to/indraA 1M-parameter OCR model that beats PaddleOCR and Tesseract on CPU
fudan-generative-vision/RemorySoft memory that survives context compaction for LLM agents
google-pytorch/torch_tpuA PyTorch Backend That Runs Models Directly on Google TPUs

See all LLMs & ML repositories →

Metrics

Star growth and Trending appearances (last 30 days)

Other notable repositories in the same category (LLMs & ML)

Get the weekly digest by email