NVIDIA/personaplex
Full-duplex speech model with voice and role control
View on index · View in 3D Map
Related repos
- AI model for zero-shot speech editing and text-to-speech
- Framework for conversational voice agents
- Text-to-dialogue model, clones voices
- Trains text-to-speech models with 2000x realtime generation on GPU
- open-source text-to-speech with voice cloning and emotion control
- local ai voice assistant stack with home assistant, whisper, piper, and wake word, gpu-ready, low vram
- Create videos of multiple characters having conversations or singing together, all driven by audio input
- Voice assistant with local processing
- Voice assistant with n8n and Home Assistant integrations
- Voice AI repo for context-aware audio conversation models
