A developer trained a speech model that parrots speech using Pink Trombone, a vocal tract simulator, and released it at samuel.vvolhejn.com with code on GitHub. The model was trained using spare GPU c…
Kyutai's 100M-parameter Pocket TTS text-to-speech model now runs entirely in the browser via OfflineTTS, enabling voice cloning through microphone recording or audio upload of up to 10 seconds, with 8…
Gradium, the voice AI developer led by CEO Neil Zeghidour, opened a public beta on July 30th for a text-to-speech model designed to pronounce phone numbers, email addresses, IBANs and time expressions…
Paris-based voice AI startup Gradium extended its seed financing to $100 million, adding Nvidia as a new investor and opening a San Francisco Bay Area office. The company, founded by former Kyutai res…
Kyutai and the Mirelo team released MuScriptor, an open-weight decoder-only Transformer for multi-instrument music transcription to MIDI. The model, trained on synthetic and real recordings across thr…
Gradium, a Paris-based voice AI startup backed by Nvidia, raised $100M to commercialize its audio-native language model that achieves sub-200ms latency, beating human conversation turn-taking baseline…
Gradium, an AI startup spun out of Kyutai, raised a $100 million seed extension backed by Nvidia to accelerate development of real-time speech models and expand into the San Francisco Bay Area. The fu…
Paris-based AI voice startup Gradium raised $100 million in a seed round reopened to new investors, including Nvidia. The company plans to use the funds to open a Bay Area office and compete for talen…
Researchers from General Intuition, Kyutai, and Epic Games released MIRA, a 5-billion-parameter latent diffusion world model that generates real-time 2v2 Rocket League matches at 20 FPS on a single GP…
General Intuition and Kyutai released MIRA on July 6th, a playable multiplayer world model that simulates a four-player Rocket League-style match in real time using a 5B-parameter diffusion transforme…
Thinking Machines released TML-Interaction-Small, a 276B parameter mixture-of-experts model with 12B active parameters, advancing real-time voice interaction by processing audio and images in under 20…