This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Free, open-source dictation for Mac. Hold Option, speak, and release to paste. Transcription and optional cleanup run locally, with models you choose to fit your hardware. A custom dictionary helps with names, product names, and technical terms. Reply suggestions (alpha, off by default) use local models to suggest replies from conversation context in permitted apps. Pick a suggestion to paste; nothing is sent automatically. No account or subscription. App code is MIT-licensed.
Hey Product Hunt! 👋
I built Open Flow because I wanted a free dictation tool that kept my voice on my Mac and let me choose how much of my hardware to use.
If you’re exploring alternatives to Wispr Flow or Superwhisper, that’s the idea behind this project: local processing, open source, and control over the models.
The workflow is simple: hold Option, speak, and release. Your words go into whichever text field you’re using.
Under the hood, whisper.cpp handles transcription with Metal acceleration. An optional local model, powered by llama.cpp, removes fillers and false starts. You can choose the transcription and cleanup models separately to balance accuracy, speed, and memory use.
One design decision I care about is keeping cleanup conservative. I want it to remove the “ums” without rewriting what you meant.
The app’s code is MIT-licensed, and dictation works offline once the models are downloaded.
I’d love feedback from people who already use dictation: what makes you go back to typing? Accuracy, delay, technical vocabulary, or cleanup that changes your words?
Source and downloads: https://github.com/Fraank98/open...
No comment highlights available yet. Please check back later!
About Open Flow on Product Hunt
“Free, open-source Mac dictation that runs locally”
Open Flow was submitted on Product Hunt and earned 2 upvotes and 1 comments, placing #148 on the daily leaderboard. Free, open-source dictation for Mac. Hold Option, speak, and release to paste. Transcription and optional cleanup run locally, with models you choose to fit your hardware. A custom dictionary helps with names, product names, and technical terms. Reply suggestions (alpha, off by default) use local models to suggest replies from conversation context in permitted apps. Pick a suggestion to paste; nothing is sent automatically. No account or subscription. App code is MIT-licensed.
Open Flow was featured in Mac (103.8k followers), Productivity (663.7k followers), Open Source (69k followers) and GitHub (41.4k followers) on Product Hunt. Together, these topics include over 231k products, making this a competitive space to launch in.
Who hunted Open Flow?
Open Flow was hunted by Danilo Franco. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Open Flow stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Danilo Franco