https://bestofai.io/tags/speech/Recent content in Speech on Best of AIHugoen-USSat, 03 Oct 2026 00:00:00 +0000https://bestofai.io/models/nemotron-3-diarization/Sat, 03 Oct 2026 00:00:00 +0000https://bestofai.io/models/nemotron-3-diarization/<p>NVIDIA released Nemotron 3 Diarization on September 23, 2026, a 100-million-parameter open-weight model that tracks up to eight overlapping speakers in real-time streaming audio. It targets call-center and meeting-transcription pipelines that need to know who said what as the audio comes in, rather than after the fact.</p>https://bestofai.io/models/qwen-audio-3-1-realtime/Sat, 03 Oct 2026 00:00:00 +0000https://bestofai.io/models/qwen-audio-3-1-realtime/<p>Alibaba released Qwen-Audio-3.1-Realtime on September 28, 2026 as the flagship of a five-model Qwen-Audio-3.1 stack that also covers speech recognition and text-to-speech. It&rsquo;s built for full-duplex voice agents, meaning it can listen and respond at the same time and decide mid-conversation when to speak versus when to call an external tool.</p>