Drop audio here or browse
MP3, WAV, OGG, M4A, FLAC · Max 50 MB
Longer files may take a moment to process.
·
Language:
Duration:
How It Works
Waveform — your audio is loaded with librosa, amplitude samples are plotted with matplotlib, and the result is returned as a downloadable PNG. Supports MP3, WAV, OGG, M4A, and FLAC up to 50 MB.
Transcription — when enabled, OpenAI Whisper "base" model runs on the server. No data is sent to OpenAI — Whisper runs entirely locally. Supports 99+ languages with auto-detection.