Wispr Flow - Speak naturally, write perfectly & 3x faster in every app
by•
Wispr Flow is a Mac dictation app that lets you speak naturally and writes in your style across every application, 3x faster than typing.
With auto-edits, AI commands, and 100+ languages, Flow saves you hours by producing perfectly formatted text instantly.
Replies
Auto-edits is a game changer. I've definitely wanted to change what I've said using voice to text before, but then I usually have to go back in and do manual edits afterwards. Great feature!
I wan to use it but its not available on Linux.. waiting for it!
Love it and use it all the time! It's what Apple should have done a long time ago with their dictation
Refocus
The bet that people will choose voice over the keyboard all day is the interesting one here, and the tone matching is what makes it credible. I build a daily voice AI that calls older adults living alone, so I think a lot about voice as a primary interface for people who find screens tiring. Question for Tanay: how much of the all-day comfort came from latency versus the auto-edit layer cleaning up disfluencies? Curious which one mattered more for getting users to actually trust it.
Been using Wispr Flow for a few months now and the thing that surprised me most is how well it handles mixed-language input.
Whispr flow has been part of my daily stack for over 5 months now I'm averaging 200k words a month and average 120wpm, I never knew I could flow so well until i downloaded Whispr Flow. Love this product.
The context-aware formatting is what separates Wispr from simple dictation apps, knowing that 'reply to John's email' needs a different tone than 'add to my notes' is a hard problem most voice tools ignore completely. Curious: how does Flow handle industry-specific jargon for fields like medicine or law where misrecognition is costly?
The zero-edit framing is the right thing to chase. Most dictation tools win on word error rate and still lose the user, because the time you save gets spent fixing tone. The auto-edit on mid-sentence corrections is the detail that tells me you actually watched how people talk, not just how they read. How does it hold up on jargon-heavy speech, the kind of call full of tool names and acronyms.
Love the vision of making voice interfaces useful everywhere. I’m curious: how does Flow decide when to preserve my raw spoken wording versus polishing it into a more structured writing style? For example, if I’m using it in Slack vs. email vs. ChatGPT, does it adapt automatically to the context?