SInES Tools: Sound Classifier (Audio Spectrogram Transformer)
(AI based batch sound classification with transformers.js and ast_finetuned_audioset)

 

1. Click on "Start" to reset all values on default and wait for the AI Model to load entirely.
2. Upload one or multiple mp3 oder wav audio file(s) (duration: more than 3 seconds).
3. optional: If you have uploaded multiple audio files to analyze them in a batch:
   Additionally, export a table for each file containing all individual values over time as a .zip file
4. Click on "Analyse" to start the detection process (Browser may pause slightly).
5. optional (Single-File only): View the classified sounds in the plot (move the mouse over the plot to listen).
6. Click on "Show JS Arrays" oder "Export CSV", to save the timeline data or batch statistics.

Loading AI Model... Please wait.

Sound Classifier © 2026 by Christoph Reuter and SInES (last modified: 24.6.2026) is licensed under CC BY 4.0
Translation of the Chinese version of the website: Li Hao
How to cite: Reuter, C. (2026). SInES Tools: Sound Classifier. Web Application https://sinestools.univie.ac.at/sound_classifier.htm