Block releases Dessa, a full-duplex speech model trained only on speech
AIBlock's AI research lab announces Dessa, a speech-to-speech model that listens and talks at the same time, trained only on human conversation audio with no text or pretrained models. Block says it trained Dessa on one NVIDIA GB200 NVL72 rack, compared with 1,016 H100 GPUs used for Kyutai's Moshi, and that it runs locally on a MacBook Pro M4 Max faster than real time.
Loading source posts…
Source details
MarkTechPost · Michal Sutter · marktechpost.comPublished · added here
Original title: Block Unveils Dessa, a Full-Duplex Speech Model Trained Only on Speech