FICHA · AUR

opensmile

A fast, real-time (audio) feature extraction utility for automatic speech, music and paralinguistic recognition research

  • audio-feature-extraction-tool
  • CLI
  • AUDIO
  • MACHINE-LEARNING
  • Launchable
  • Runs in terminal
official+codex · reviewed · Jun 3, 2026 description in en

Description

Audio features can be extracted in real time for speech, music, and paralinguistic recognition research. This helps researchers build datasets and machine-learning pipelines.

Audio analysis can process voices and sensitive recordings. Use consented data, protect outputs, and validate feature sets before publication or deployment.

How to run

SMILExtract

Commands: SMILExtract

Permissions

Permissions not analysed for this source yet.