Earlybird

Earlybird

29M-param speech-to-text that outputs words before they end

Developer ToolsArtificial IntelligenceGitHubOpen Source
▲ 86 votes5 commentsLaunched Nov 11, 2026
Visit Website
Daily #19Weekly #42Monthly #11654Yearly #185244

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.

AI Analysis

AI analysis not yet available for this product.