{
 "schema_version": 1,
 "generated": "2026-10-24",
 "repo": "NVIDIA/personaplex",
 "name": "personaplex",
 "owner": "NVIDIA",
 "slug": "nvidia-personaplex",
 "github": "https://github.com/NVIDIA/personaplex",
 "what": "PersonaPlex is NVIDIA's real-time, full-duplex speech-to-speech conversational model based on Moshi that controls persona through text role prompts and audio voice conditioning.",
 "why": "+270 stars this week, 11k total, picked up by one AI source we track",
 "language": "Python",
 "requirements": [
  "Linux with an NVIDIA GPU",
  "Opus development library",
  "A Hugging Face token with access to the model"
 ],
 "audience_note": "Speech AI researchers and developers building low-latency voice agents with a consistent persona.",
 "risk": "none",
 "section": "earlier",
 "weekly_rank": null,
 "category": "Research",
 "url": "https://dedupedai.com/use-cases/nvidia-personaplex/",
 "use_case_count": 3,
 "use_cases": [
  {
   "id": "nvidia-personaplex--run-full-duplex-voice-agent-web-ui",
   "title": "Talk to a full-duplex voice model in your browser",
   "best": true,
   "url": "https://dedupedai.com/use-cases/nvidia-personaplex/run-full-duplex-voice-agent-web-ui/",
   "json": "https://dedupedai.com/use-cases/u/nvidia-personaplex/run-full-duplex-voice-agent-web-ui.json"
  },
  {
   "id": "nvidia-personaplex--give-voice-agent-a-persona",
   "title": "Give a voice agent a role and a voice",
   "best": false,
   "url": "https://dedupedai.com/use-cases/nvidia-personaplex/give-voice-agent-a-persona/",
   "json": "https://dedupedai.com/use-cases/u/nvidia-personaplex/give-voice-agent-a-persona.json"
  },
  {
   "id": "nvidia-personaplex--batch-generate-spoken-replies-offline",
   "title": "Generate spoken replies from recorded input offline",
   "best": false,
   "url": "https://dedupedai.com/use-cases/nvidia-personaplex/batch-generate-spoken-replies-offline/",
   "json": "https://dedupedai.com/use-cases/u/nvidia-personaplex/batch-generate-spoken-replies-offline.json"
  }
 ],
 "disclaimer": "Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk."
}