audeering/opensmile

The Munich Open-Source Large-Scale Multimedia Feature Extractor

56
/ 100
Established

This toolkit helps researchers and developers working with audio data to extract meaningful information from speech and music. You provide raw audio files, and it processes them to output features like speaker identity, emotional content, or musical tempo. This is ideal for academics or engineers developing systems for tasks like automatic speech recognition or music analysis.

787 stars.

Use this if you need to extract detailed, low-level features from audio recordings for research or application development in speech or music analysis.

Not ideal if you need a high-level audio classification tool without needing to delve into feature extraction, or if you require commercial use without purchasing a license.

speech-recognition music-analysis speaker-identification emotion-recognition audio-feature-extraction
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

787

Forks

97

Language

C++

License

Last pushed

Jan 26, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/audeering/opensmile"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.