local speech-to-text is shockingly fast on Apple Silicon

Show HN: local speech-to-text is shockingly fast on Apple Silicon

local speech-to-text is shockingly fast on Apple Silicon is active in the show hn launch space.

Profile

TL;DR: How far can you go with local ML on a Mac? We built a dictation app to find out. It turned out, pretty far! On a stock M-series Mac, end-to-end speech → text → LLM cleanup runs in under 1s on a typical sentence.What is this? A local dictation app for macOS. It’s a free alternative to Wispr Flow, SuperWhisper, or MacWhisper. Since it runs entirely on YOUR device we made it free. There’s no servers to maintain so we couldn’t find anything to charge you for. We were playing with Apple Silicon and it turned into something usable, so we’re releasing it.If you've written off on-device transcription before, it’s worth another look. Apple Silicon + MLX is seriously fast. We've been using it d

Its activity falls under show hn launch; the profile below is assembled from public directory data.

The company is listed at the Show HN launch stage of development.

Website: www.getonit.ai/dictate