Model reference · open weights

voice-activity-detection

Audio pyannote Speech→text 1 build Open weights 4.4M dl/mo

voice-activity-detection is an open-weight audio or speech model from pyannote.

  • voice-activity-detection is a model by pyannote designed for automatic speech recognition tasks.
  • It is published as pyannote/voice-activity-detection and operates under the MIT license.
  • The model relies on pyannote.audio 2.1 and requires an access token for use.

Summary of the pyannote/voice-activity-detection model card, 2026-10-01

What it is

Released bypyannote
Released2022-03-02

How it works

How audio & music work

Audio or textinputAudio modelrecognise / synthesiseText or audiooutputSpeech-to-text turns audio into text; text-to-speech and music models turn text into audio.
© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms