audio-speaker-tools - Speaker separation and voice comparison tools
Separate speakers from audio files, compare voice samples, and process audio segments using Demucs, pyannote, and Resemblyzer.
Tags
Updated: 2026-03-24Capabilities
Typical Inputs
Typical Outputs
What this skill does
- separate speakers from audio
- compare voice samples
- extract audio segments
- measure speaker similarity
- validate speaker diarization results
- convert audio formats
Inputs
- Audio files
- HuggingFace token
Outputs
- Speaker WAV files
- RTTM file
- JSON segments metadata
- Voice similarity scores
Requirements
- Python 3.9+
- ffmpeg
- HuggingFace token
- HuggingFace model access