1:06LiveKit Inference now runs cascaded, turn based and full duplex voice agents@livekit · 197 views · 2026-10-15LiveKitVoice Agent
0:35Microsoft MAI-Transcribe-2-Streaming tops Artificial Analysis: 2.5% WER with first partials ~100ms after speech — Japanese streamer demos it live: "the meeting-notes app era is over"@studio_yebisu · 605 views · 2026-10-01Speech-To-TextStreaming
0:28Audio8 ASR Infinite: rolling KV cache enables 24/7 drift-free streaming ASR (Apache 2.0)@_akhaliq · 698 views · 2026-09-30Audio8 ASR InfiniteStreaming ASR
0:54Nemotron 3 Diarization tested: 100M-param real-time speaker diarization, better than expected locally@ouchi · 697 views · 2026-09-27NVIDIANemotron 3
3:28Daily introduces PhoneLLM, an open model for voice agents@kwindla · 656 views · 2026-08-27PhoneLLMVoice Agent