Renaissance Labs

Atlas / Europe

Independent company · Gilching, Germany

audEERING

Munich-area audio AI company and maker of the openSMILE toolkit and open speech emotion and age-gender models.

speech emotion recognitionaudio analysis

Gilching, Germany

Founded
2012
Type
Independent company
Based in
Gilching, Germany
Key papers
1
Featured projects
7

About

audEERING was founded in 2012 as a spin-off of Technical University of Munich research, with Dagmar Schuller, Florian Eyben, Björn Schuller and Martin Wöllmer named as founders in a 2012 report. It is based in Gilching near Munich.

openSMILE began in 2008 at TUM within the EU SEMAINE project. In 2013 audEERING obtained the rights and published version 2.0 under a research licence. The toolkit is free for research and personal use, while commercial users need a licence, so it is source-available rather than fully open.

The company also maintains open repositories on audio machine learning, including the w2v2-how-to guide and wav2vec2-based emotion and age-gender models on Hugging Face.

Mission and ambitions

audEERING develops audio analysis and speech emotion technology and shares research tooling with the scientific community while selling commercial products.

Known for

  1. 01

    openSMILE feature extraction

  2. 02

    Speech emotion recognition models

  3. 03

    Age and gender audio models

  4. 04

    TUM spin-off audio AI

Milestones

  1. 2008

    openSMILE begins

    Eyben, Wöllmer and Schuller started openSMILE at TUM within the SEMAINE project.

  2. 2012

    Company founded

    audEERING was founded in Munich as a TUM spin-off.

  3. 2013

    openSMILE 2.0

    The company acquired the code rights and released version 2.0 under a research licence.

  4. 2020

    opensmile Python repository

    A new openSMILE repository was created on the audeering GitHub organization.

  5. 2022

    w2v2-how-to

    Published a guide and code for wav2vec2 emotion work.

Open source

GitHubgithub.com/audeering
  • The Munich Open-Source Large-Scale Multimedia Feature Extractor (859 stars)

  • How to use our public wav2vec2 dimensional emotion model (564 stars)

  • Python package for openSMILE (337 stars)

  • Utils and data sets for audio and PyTorch (87 stars)

Hugging Facehuggingface.co/audeering

Research papers

Notable releases

Openness

Commercial company with a large public footprint: tools and several models are open on GitHub and Hugging Face.

People

Listed from the lab's own pages and public profiles.

Contact and community

Contact through the company website.

Sources

Compiled from the lab's public pages, Hugging Face and GitHub. Last checked 2026-11-17. Something wrong or out of date? Tell us on Discord.

Labs nearby