Audio
Tools will load when you run.Audio to Text Transcription≈
Transcribe audio locally with multilingual Whisper and download text with a timestamp report.
Your result.
How to use Audio to Text Transcription
- Choose your MP3, WAV, FLAC, OGG, AAC, M4A, MP4, AIF, AIFF, OPUS, WMA.
- Upload an audio clip up to 5 minutes and choose a language, or use automatic detection. The model downloads on first use.
- Download the text and JSON timestamp report. Review the result for recognition errors.
Formats and requirements
- Input formats
- MP3, WAV, FLAC, OGG, AAC, M4A, MP4, AIF, AIFF, OPUS, WMA
- Output
- plain text
- Availability
- Free in your browser and through the CLI
- Files per operation
- 1
- Browser file limit
- 32 MiB per file, 32 MiB total
What to expect
Transcribes locally with Whisper tiny (multilingual). The model downloads on first use; no audio is uploaded. Recognition can make mistakes. Browser clips are limited to 5 minutes.
Do my files leave my device?
No. Thanks to advanced file-processing technology, your files are processed directly on your device, inside your browser. OneKit does not receive your input files or results. Required public processing libraries may download when you first use the tool.
File privacy and local processing →