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).

Product upvotes vs the next 3

Waiting for data. Loading

Product comments vs the next 3

Waiting for data. Loading

Product upvote speed vs the next 3

Waiting for data. Loading

Product upvotes and comments

Waiting for data. Loading

Product vs the next 3

Loading

Lowspeak

AI speech-to-text in every Mac app, online or offline

Hold fn, talk, let go: your words appear wherever the cursor is, in any Mac app. Online with Groq (free on its free plan) or OpenAI, offline with Whisper and NVIDIA Parakeet on your Mac. 100% Rust on native AppKit: 17 MB, about 45 MB of memory, text about 0.4 s after you let go. Vocabulary, cleanup, per-app formatting, hands-free mode, 35 languages. Open source, no account, no telemetry.

Top comment

Hi Product Hunt! I'm Sven, and I built Lowspeak so I could talk instead of type in any app on my Mac.

How it works: hold fn, talk, let go. The text appears where your cursor is: in Mail, Slack, your editor or the terminal.

What makes it different:

• Online and offline: Groq or OpenAI with your own key, or Whisper and NVIDIA Parakeet entirely on your Mac. If the network drops, a local model takes over the same recording.

• Free and fast online: on Groq's free plan, transcription costs nothing within its daily limits. Lowspeak opens the connection while you are still speaking, so the text is there about 0.4 seconds after you let go.

• Ultrafast and small: 100% Rust on native AppKit, no Electron. 17 MB on disk, about 45 MB of memory online.

• More than dictation: a vocabulary for names and terms, optional cleanup of filler words and grammar, formatting for the app you dictate into, a hands-free mode for up to five minutes, your last ten dictations in the menu, 35 languages.

• Open source: MIT or Apache-2.0, no account, no telemetry.

It runs on macOS 14 or later, on Apple Silicon and Intel. With Homebrew: brew install --cask sventmueller/tap/lowspeak

Where does dictation still let you down: accents, technical terms, a language that comes out wrong? I'd love to hear it.

About Lowspeak on Product Hunt

“AI speech-to-text in every Mac app, online or offline”

Lowspeak was submitted on Product Hunt and earned 2 upvotes and 1 comments, placing #133 on the daily leaderboard. Hold fn, talk, let go: your words appear wherever the cursor is, in any Mac app. Online with Groq (free on its free plan) or OpenAI, offline with Whisper and NVIDIA Parakeet on your Mac. 100% Rust on native AppKit: 17 MB, about 45 MB of memory, text about 0.4 s after you let go. Vocabulary, cleanup, per-app formatting, hands-free mode, 35 languages. Open source, no account, no telemetry.

On the analytics side, Lowspeak competes within Mac, Open Source, Artificial Intelligence and GitHub — topics that collectively have 698.5k followers on Product Hunt. The dashboard above tracks how Lowspeak performed against the three products that launched closest to it on the same day.

Who hunted Lowspeak?

Lowspeak was hunted by Sven Müller. 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.

For a complete overview of Lowspeak including community comment highlights and product details, visit the product overview.