Instant dictation for desktop. Press a shortcut, speak, and instantly get accurate text on your clipboard—perfect for emails, coding, AI prompts, or brain dumps.
open source and local is the right call for a dictation tool specifically, since the whole point is you're speaking things you'd never type into a random cloud service. curious how the accuracy holds up on technical vocabulary though, variable names, library names, that kind of thing tends to be where local models fall over compared to the big hosted ones. is there a custom vocabulary or fine tuning option for that or is it running as-is out of the box.
About VoiceGecko on Product Hunt
“Open source, local voice-to-text”
VoiceGecko launched on Product Hunt on August 11th, 2026 and earned 103 upvotes and 2 comments, placing #14 on the daily leaderboard. Instant dictation for desktop. Press a shortcut, speak, and instantly get accurate text on your clipboard—perfect for emails, coding, AI prompts, or brain dumps.
On the analytics side, VoiceGecko competes within Developer Tools and Audio — topics that collectively have 520.6k followers on Product Hunt. The dashboard above tracks how VoiceGecko performed against the three products that launched closest to it on the same day.
Who hunted VoiceGecko?
VoiceGecko was hunted by Luke. 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.
Luke
open source and local is the right call for a dictation tool specifically, since the whole point is you're speaking things you'd never type into a random cloud service. curious how the accuracy holds up on technical vocabulary though, variable names, library names, that kind of thing tends to be where local models fall over compared to the big hosted ones. is there a custom vocabulary or fine tuning option for that or is it running as-is out of the box.