iohann.s.titov@gmail.com Ivan S. Titov Install the pyannote-audio command-line tool (pulls dev-python/typer) pyannote.audio is a deep-learning toolkit for speaker diarization, voice activity detection, overlapped speech detection, and speaker embedding. The Python package alone does not include any pretrained models; running pretrained pipelines such as pyannote/speaker-diarization-3.1 requires accepting the model terms on HuggingFace and authenticating with a HuggingFace token. pyannote-audio pyannote/pyannote-audio https://github.com/pyannote/pyannote-audio/issues