Product Thumbnail

SpeechFast

Local Whisper for Mac

Productivity
Menu Bar Apps
Audio
Visit WebsiteSee on Product Hunt

Hunted byMusMus

Hold fn and talk. SpeechFast types clean text at your cursor, in any app. Everything runs on your Mac. The speech model is downloaded once; after that, no audio and no text ever leaves your machine. It works offline, on a plane, behind a locked-down corporate network. Dictate in Mail, Slack, Notion, your code editor, anywhere you can type Filler words and false starts cleaned up with Apple Intelligence Your own vocabulary for names and jargon History of your recent dictations, stored locally

Top comment

Hey Product Hunt 👋 I'm Mustapha, and I built SpeechFast because I wanted to dictate on my Mac without my voice going to someone else's server. How it works: hold fn, talk, let go. Clean text appears at your cursor, in whatever app you're in: Mail, Slack, Notion, your code editor, a terminal. What makes it different with SuperWhisper or WisprFlow: 100% on-device. Transcription runs on your Mac's chip, with the NVIDIA Parakeet model. It's downloaded once; after that, SpeechFast works offline, even in airplane mode. An automated test fails the build if a single request leaves the Mac during a dictation. - Hands-free mode for longer thoughts, and a local history of your recent dictations. It needs a Mac with Apple Silicon (M1 or later) running macOS 26. I'd love your feedback, especially on accuracy in your language and on the apps where pasting doesn't behave. One more thing: if you know a local speech model that runs well on Apple Silicon and beats Parakeet for your language or use case, please tell me. I'm always testing new ones, and the best suggestions will make it into the app. I'll be here all day answering questions.

Comment highlights

@pixelmus Are you running Parakeet in a streaming mode with a rolling buffer, or transcribing the whole utterance after the key is released? I'm curious how it holds up on accented English and when someone switches languages mid-sentence.

Having an automated test that fails the build if anything leaves the Mac during dictation is a really reassuring detail. When pasting doesn't work in an app, does the text stay somewhere I can copy it from, like the local history?

tried it in warp terminal and it pasted clean, no weird formatting, way better than i expected for a terminal

About SpeechFast on Product Hunt

“Local Whisper for Mac”

SpeechFast launched on Product Hunt on October 18th, 2026 and earned 82 upvotes and 10 comments, placing #16 on the daily leaderboard. Hold fn and talk. SpeechFast types clean text at your cursor, in any app. Everything runs on your Mac. The speech model is downloaded once; after that, no audio and no text ever leaves your machine. It works offline, on a plane, behind a locked-down corporate network. Dictate in Mail, Slack, Notion, your code editor, anywhere you can type Filler words and false starts cleaned up with Apple Intelligence Your own vocabulary for names and jargon History of your recent dictations, stored locally

SpeechFast was featured in Productivity (663.4k followers), Menu Bar Apps (12.3k followers) and Audio (2.2k followers) on Product Hunt. Together, these topics include over 177.8k products, making this a competitive space to launch in.

Who hunted SpeechFast?

SpeechFast was hunted by Mus. 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 SpeechFast stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.