For years I paid for dictation. Superwhisper, Wispr Flow, a few subscription apps for turning voice into text.
Last week I dropped all of them for an open source project built by one guy: FreeFlow.
Some context. I write prompts all day now. Agentic coding is mostly that, and what comes out depends on what goes in. Typing a good prompt is slow. Talking is fast. So dictation stopped being a nice-to-have and became part of the actual workflow.
What sold me
It’s free and MIT. Not “free with a hidden pro tier.” Open source for real.
It doesn’t run a local model. It uses an API, Groq by default, on Whisper. For most people that’s the controversial part. What about privacy, what about offline. For me it’s the other way around: I still have Intel Macs where local models barely run, and an API hands me a top-tier model on hardware everyone already wrote off. Groq is also stupid fast.
Edit mode is where it clicked
You select text you already wrote, hit the shortcut again, and instead of dictating over it you ask for a change. “Shorten this.” “Make it bullets.” “More formal.” It rewrites, mid-prompt, by section, without your hands leaving the keyboard.
Dictating turns into a conversation with the text.
Worth a look if you work with AI and agentic coding. Less friction between the idea and the prompt: github.com/zachlatta/freeflow