AI Transcribe

Generate transcripts from audio or video using fully local AI processing.

⚡ 100% Local (No Upload)

This task runs fully on your device with no uploads.

Upload audio or video

MP3, WAV, M4A, MP4, and WEBM supported. Nothing leaves your device.

⚡ 100% Local (No Upload)🔒 Runs locally on your deviceNo Uploads. No Tracking.Offline cache initializing

Drag and drop your file here

or click to upload

Supported: audio/*, video/*

Max file size: 1.00 GB

One-click local automations for audio cleanup and transcription.

Configure model, language, and enhancement pipeline.

WebGPU unavailable. Using WebAssembly.

AI Presets

Model

Fast

Quick drafts with the smallest model.

Balanced

Balanced accuracy and speed.

High Accuracy

Largest local model with best accuracy.

Language

Translate to EnglishInclude timestampsSpeaker segmentation

Audio Enhancements

Noise reductionVoice enhancementSilence trimming

Chain local steps: Audio Enhance → Transcribe

Step 1

Audio Enhance

Noise reduction, voice enhancement, and silence trimming.

Step 2

Transcribe

Run Whisper locally with on-device inference.

Upload files to see live queue progress.

Upload media to generate a transcript.

Stored only in this browser using IndexedDB.

No saved transcription sessions yet.