Skip to main content
🎵

Pyannote Audio

Open-source neural speaker diarization toolkit

Audio & Speech
Pyannote Audio logo

Pyannote Audio

Open-source neural speaker diarization toolkit

pyannote.audio is an open-source Python toolkit for speaker diarization and related tasks that provides state-of-the-art pre-trained models for identifying who spoke when in audio recordings. The toolkit integrates with other speech processing libraries and allows fine-tuning on custom speaker data. Researchers, developers, and data scientists use pyannote.audio for speaker diarization in podcasts, meetings, and conversational AI applications.

Key Features

  • Speaker diarization
  • Pre-trained models
  • Python toolkit
  • Fine-tuning
  • Open source
  • HuggingFace integration
#speaker-diarization#open-source#speech#research#python

Get Started

Visit Pyannote Audio
🟢
Free
Completely free to use

Quick Info

Category
Audio & Speech
Pricing
Free

More Audio & Speech Tools