Open models for real-time voice pipelines: VAD, diarization, streaming ASR, TTS, full-duplex speech, and talking-head animation.
-
pyannote/voice-activity-detection
Automatic Speech Recognition • Updated • 4.5M • 241 -
pyannote/speaker-diarization-3.1
Automatic Speech Recognition • Updated • 9.77M • 3.2k -
nvidia/parakeet-tdt-0.6b-v2
Automatic Speech Recognition • Updated • 279k • 1.54k -
nvidia/nemotron-3.5-asr-streaming-0.6b
Automatic Speech Recognition • 0.6B • Updated • 922k • • 1.07k