Sound event finder · AI beta
Sound event finder · AI beta — Sound candidates / select segments / WAV / JSON
One browser-decodable recording · 32 MiB / 60 seconds. YAMNet predicts sound labels in ~0.975-second windows. English labels and scores are predictions. Select segments and save WAV. Music / overlapping sounds can be wrong; selected clips retain their background audio.
- Select audio
- Check effects and output settings
- Process, listen and save
Usage example
- Example input
recording.wav- Expected result
Selected sound-event windows joined as WAV + original-time JSON
Examples are illustrative. Actual results depend on the source file and settings.
Examples and limitations
Sound candidates / select segments / WAV / JSON
Input and output
- Supported input
audio/* · .wav · .mp3 · .m4a · .ogg · .flac · .webm- Saved output
WAV · JSON
Usage example
- Example input
recording.wav- Expected result
Selected sound-event windows joined as WAV + original-time JSON
Examples are illustrative. Actual results depend on the source file and settings.
Limits and checks
- One browser-decodable recording · 32 MiB / 60 seconds. YAMNet predicts sound labels in ~0.975-second windows. English labels and scores are predictions. Select segments and save WAV. Music / overlapping sounds can be wrong; selected clips retain their background audio.
- Models and runtimes download from this Site. Selected files are never uploaded. Review AI predictions before saving.