Post
37
🎉 More than 400,000 people have now downloaded pyannote models from Hugging Face. Thank you!
People use pyannote to build transcription tools, meeting assistants, call analytics, media workflows and Voice AI training data. In every case, a system needs to know who spoke when before it can understand a conversation.
🔓 Open source: pyannote/speaker-diarization-community-1
💻 Code: github.com/pyannote/pyannote-audio
🚀 Production: Precision-3 on pyannote.ai
💬 Show us what you’ve built at our Discord Office Hours on 19th November 2026 and win $50 in free credits to test our commercial models on their own audio: https://discord.gg/JnXxcc9SC?event=1554052903675756554
What are you building with pyannote.audio?
People use pyannote to build transcription tools, meeting assistants, call analytics, media workflows and Voice AI training data. In every case, a system needs to know who spoke when before it can understand a conversation.
🔓 Open source: pyannote/speaker-diarization-community-1
💻 Code: github.com/pyannote/pyannote-audio
🚀 Production: Precision-3 on pyannote.ai
💬 Show us what you’ve built at our Discord Office Hours on 19th November 2026 and win $50 in free credits to test our commercial models on their own audio: https://discord.gg/JnXxcc9SC?event=1554052903675756554
What are you building with pyannote.audio?