Utilities

This category is for tools that solve an everyday problem without asking you to hand your data to a cloud service. The current entry is small, but the principle matters: the same capability, running locally, under your control.

WhisperUI

WhisperUI is a local audio transcription desktop application. It runs OpenAI’s Whisper model entirely on your machine through a PyQt6 interface. No API key, no upload, no cloud — just audio in and transcripts out.

It supports MP3, WAV, M4A, and other formats via FFmpeg, offers multiple model sizes for speed-vs-accuracy tradeoffs, and exports to plain text, SRT, VTT, or JSON with word-level timestamps.

Why Local-First Matters

For client interviews, legal recordings, business meetings, or personal voice memos, sending audio to a cloud transcription service is a non-starter. WhisperUI keeps the entire pipeline — audio processing, transcription, timestamping, export — on the local machine.

Built with Python, PyQt6, OpenAI Whisper, and FFmpeg. Your audio never leaves your machine.