audio-speaker-tools - Speaker Separation and Voice Comparison Tools
Separate speakers from audio and measure voice similarity between files
Tags
Updated: 2026-03-24Capabilities
Typical Inputs
Typical Outputs
What this skill does
- separate speakers from audio
- extract audio segments
- compare voice samples
- measure voice similarity
- validate speaker diarization
Inputs
- audio files
- HuggingFace token
- output directory
Outputs
- separated speaker audio files
- voice similarity scores
- RTTM timestamp files
- segment metadata files
Requirements
- Python 3.9+
- ffmpeg
- HuggingFace token