Audio Transcription (AI)

Transcribe audio to text using OpenAI Whisper AI, running entirely in your browser. Supports 10+ languages. Your audio never leaves your device.

Drop files here or click to browse

Accepted: .mp3,.wav,.m4a,.ogg,.flac,.webm,audio/mpeg,audio/wav,audio/mp4,audio/ogg,audio/flac,audio/webm

OpenAI Whisper (via @huggingface/transformers) runs entirely in your browser — audio is never uploaded.

Frequently Asked Questions

What AI model is used for transcription?
OpenAI Whisper (tiny model, ~40MB) running via Transformers.js. It downloads once and is cached for future use.
Which audio formats are supported?
MP3, WAV, M4A, OGG, FLAC, and WebM audio files.
Is my audio uploaded to any server?
No — the Whisper AI model runs entirely in your browser. Your audio never leaves your device.
Why is the first transcription slow?
The AI model (~40MB) downloads on first use and is cached. Subsequent transcriptions use the cached model and are faster.
Can I download subtitles?
Yes — download as .txt (plain text) or .srt (subtitle file with timestamps for video players).