Get the speaker-label token (optional)

1. 1

   Sign up for HuggingFace

   Create a free account and sign in.

   huggingface.co/join ↗
2. 2

   Accept the model gate

   On the pyannote model page, click “Agree” to accept the terms.

   huggingface.co/pyannote/speaker-diarization-community-1 ↗
3. 3

   Create an access token

   Issue a token with read access.

   huggingface.co/settings/tokens ↗
4. 4

   Paste into the app

   Settings → Speaker labels. It’s stored encrypted in the Keychain and never sent anywhere.

The token is used only to authenticate with HuggingFace. Official guide: huggingface.co/docs/hub/security-tokens ↗

Back to the full setup guide FAQ on speaker labels & supported apps