Organization
5 Interestana reports mention Kyutai, newest first. Each links back to its publisher, with an AI summary of the original reporting where we have found no publisher terms that forbid one.
Gradium has open-sourced Phonon, a family of small on-device text-to-speech models. The 31M parameter English Phonon model, fitting in a 64.5 MB file, ships under Apache 2.0, enabling natural speech without cloud calls or GPUs.
Kyutai, Inria, and École des Ponts have released REKI, a 2.4B parameter vision-language-action model for robot manipulation. The model uses efficient memory and performs well on out-of-distribution benchmarks, with weights available on Hugging Face.
Kyutai has released Voice of Reason, a pair of open-weight speech-to-speech models designed to solve mathematical problems spoken aloud. These models operate without an intermediate transcription step or a separate text-based large language model (LLM) in the processing loop, directly…
Paris-based Gradium, a voice AI company that originated from the Kyutai research lab, has introduced Voice Design, a novel system capable of generating entirely new synthetic voices based on written descriptions.
Kyutai and Mirelo released MuScriptor this week, an open-weight decoder-only Transformer model designed to transcribe multi-instrument music into MIDI format. Automatic Music Transcription (AMT) has historically struggled with complex mixes, but MuScriptor aims to bridge this gap by training…