Block's AI research lab, led by Jack Dorsey's fintech company, released a research preview of Dessa, a full-duplex voice conversation model trained exclusively on human conversational speech. Unlike conventional models, Dessa was built from scratch without text data or pretrained foundations, enabling it to listen and speak simultaneously.
The model was trained using a single NVIDIA GB200 NVL72 GPU and can run locally on a MacBook Pro M4 Max or higher at faster-than-real-time speed. Project lead Ragavan Thurairatnam described the release as "the GPT-3 moment for voice." Dessa is not yet broadly available; Block has published recorded conversation demos and granted early access to a small group of AI safety researchers.
Block Releases Dessa, a Voice-Only Conversational AI Model That Runs Locally on MacBook
Avertissement : Le contenu proposé sur Phemex News est à titre informatif uniquement. Nous ne garantissons pas la qualité, l'exactitude ou l'exhaustivité des informations provenant d'articles tiers. Ce contenu ne constitue pas un conseil financier ou d'investissement. Nous vous recommandons vivement d'effectuer vos propres recherches et de consulter un conseiller financier qualifié avant toute décision d'investissement.
