29M-param speech-to-text that outputs words before they end
Earlybird is a 29M-parameter, 17 MB on-device speech-to-text model that predicts each word correctly about 90 ms before the speaker finishes it, with a confidence on every word. Built for voice agents that need to act sooner. Open weights and code.
I've been building voice agents and kept running into the same delay: speech-to-text waits for each word to end before it shows it, so the agent can't start working until then. Earlybird outputs words before the speaker finishes speaking them. On audiobook speech the median word is predicted correctly 90 ms before it's fully spoken, where other streaming models get it right 90 to 400 ms after. The model is 17 MB and runs on a CPU.
About Earlybird on Product Hunt
“29M-param speech-to-text that outputs words before they end”
Earlybird launched on Product Hunt on November 11th, 2026 and earned 90 upvotes and 5 comments, placing #16 on the daily leaderboard. Earlybird is a 29M-parameter, 17 MB on-device speech-to-text model that predicts each word correctly about 90 ms before the speaker finishes it, with a confidence on every word. Built for voice agents that need to act sooner. Open weights and code.
On the analytics side, Earlybird competes within Open Source, Developer Tools, Artificial Intelligence and GitHub — topics that collectively have 1.1M followers on Product Hunt. The dashboard above tracks how Earlybird performed against the three products that launched closest to it on the same day.
Who hunted Earlybird?
Earlybird was hunted by Sahil Mahendrakar. 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 Earlybird including community comment highlights and product details, visit the product overview.
Sahil Mahendrakar
Hey Product Hunt! I'm Sahil.
I've been building voice agents and kept running into the same delay: speech-to-text waits for each word to end before it shows it, so the agent can't start working until then. Earlybird outputs words before the speaker finishes speaking them. On audiobook speech the median word is predicted correctly 90 ms before it's fully spoken, where other streaming models get it right 90 to 400 ms after. The model is 17 MB and runs on a CPU.