# Wispr Flow

By Saurabh Kumar · TIL note, Oct 8, 2026 · Tags: macos, speech-to-text

Source: https://saurabh-kumar.com/til/1791460800/

Back on [Wispr Flow](https://wisprflow.ai/) after six months on local speech-to-text ([FluidVoice](https://github.com/altic-dev/FluidVoice) with Parakeet, plus Whisper). Local transcription is fine. The cleanup is what's missing: fixing misheard jargon ate the time dictation saved. Flow's correction pass, OS-level integration and phone keyboard win. It matters more now because models follow high-level intent well: I speak the intent plus constraints in one go and let the LLM structure it. Whisper mode works even when you speak softly. Want to try it? My [referral link](https://wisprflow.ai/r?SAURABH2220) gets you a free month of Pro, and I get one once you've dictated 2,000 words.