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.
Predicting the word 90 ms early is a clever trade — in a voice agent, that 90 ms is often the difference between feeling instant and feeling laggy. What I like most is the confidence on every word: that gives the agent something real to decide on, act now on the high-confidence words and wait on the uncertain ones. At 17 MB on-device with open weights, this is small enough to actually ship inside an app. Curious how it holds up on noisy, real-world audio versus clean recordings.
Getting the word before it's finished is a neat trick. Does it work for languages other than English yet?
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.
Earlybird was featured in Open Source (69.1k followers), Developer Tools (523k followers), Artificial Intelligence (483.5k followers) and GitHub (41.5k followers) on Product Hunt. Together, these topics include over 282.8k products, making this a competitive space to launch in.
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.
Want to see how Earlybird stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
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.