Submissions from kyutai.org

		Kyutai MuScriptor: Automatic Multi-Instrument Transcription (kyutai.org)
		1 point by Sebastian_09 45 days ago \| past
		Post-training speech models for better interactivity (kyutai.org)
		2 points by pr337h4m 3 months ago \| past
		Hibiki-Zero:real-time and multilingual speech translation model (kyutai.org)
		1 point by pain_perdu 7 months ago \| past
		Pocket TTS: A high quality TTS that gives your CPU a voice (kyutai.org)
		635 points by pain_perdu 8 months ago \| past \| 158 comments
		CASA: Cross-Attention via Self-Attention (kyutai.org)
		2 points by swyx 9 months ago \| past
		Neural audio codecs: how to get audio into LLMs (kyutai.org)
		428 points by karimf 11 months ago \| past \| 119 comments
		Kyutai STT – A speech-to-text optimized for real-time usage (kyutai.org)
		6 points by ajuhasz on June 19, 2025 \| past
		Unmute: Make LLMs Listen and Speak (kyutai.org)
		3 points by ilnmtlbnm on May 27, 2025 \| past \| 1 comment
		MoshiVis – an Open-Source Vision Speech Model (VSM) (kyutai.org)
		2 points by falcor84 on March 25, 2025 \| past
		Kyutai unveils today the first voice-enabled AI openly accessible to all [pdf] (kyutai.org)
		25 points by elcomet on July 3, 2024 \| past \| 10 comments
		Kyutai: Open Science AI Lab (kyutai.org)
		2 points by gfortaine on Nov 19, 2023 \| past