
Earlybird精选
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.
2026-11-11 同榜
801
ScroogeFrog AIAI ad fraud detection that protects your marketing budget ▲ 30002
Nod by n8nOpen source personal agent with its own computer▲ 29203
CALL-EMake phone calls with your AI agent (Muse, ChatGPT, Claude)▲ 25104
Scribe v3 by ElevenLabsSpeech to text with 27% fewer errors in 90+ languages▲ 17805
SkillboxOne library for your AI skills, synced to every agent▲ 15206
MiniMax H3-ImageBringing 4K image generation into the 10-second era▲ 12707
RelayDocSend for AI agents: send and receive docs with context▲ 12608
Shot.videoMulti-camera videos with the phones you already own▲ 117