Kyutai
A French AI research laboratory focused on open-source speech, audio and multimodal model research, known for open weights and efficient model design.
Timeline (last 90 days)
Moshi is a full-duplex real-time voice dialogue model released in 2024 by the French AI company Kyutai.
Kyutai released CADRE, a family of open causal diffusion video autoencoders comprising 7 models.
Kyutai, together with Inria and École des Ponts, released the REKI 2.4B model, with weights now available for download on Hugging Face.
Kyutai, together with Inria and École des Ponts, released REKI, a 2.4-billion-parameter vision-language-action (VLA) model specifically aimed at robotic manipulation tasks.
Mistral's streaming model was partly inspired by the latency stream modeling released by Kyutai, but differs in that the encoder is trained end-to-end from scratch.
All Facts (5)
Moshi is a full-duplex real-time voice dialogue model released in 2024 by the French AI company Kyutai.
50%UnverifiedMistral's streaming model was partly inspired by the latency stream modeling released by Kyutai, but differs in that the encoder is trained end-to-end from scratch.
50%UnverifiedKyutai released CADRE, a family of open causal diffusion video autoencoders comprising 7 models.
50%UnverifiedKyutai, together with Inria and École des Ponts, released the REKI 2.4B model, with weights now available for download on Hugging Face.
50%UnverifiedKyutai, together with Inria and École des Ponts, released REKI, a 2.4-billion-parameter vision-language-action (VLA) model specifically aimed at robotic manipulation tasks.
50%