dorsal / monitorES
Back to the monitor

Block announces Dessa, a full‑duplex speech‑to‑speech model trained only on conversation

AI-generated conceptual illustration for “Block announces Dessa, a full‑duplex speech‑to‑speech model trained only on conversation”.
AI-generated illustration

On October 23, 2026, Block’s in‑house AI lab unveiled Dessa, which it describes as a full‑duplex speech‑to‑speech model trained from scratch on human conversation that can listen and speak simultaneously and runs locally on a MacBook Pro M4 Max or better; Block released demo recordings, opened a public waitlist, and offered early access to a small group of AI safety researchers.

Summary

AI-assisted summary of the linked source

On October 23, 2026, Block’s in‑house AI lab unveiled Dessa, which it describes as a full‑duplex speech‑to‑speech model trained from scratch on human conversation that can listen and speak simultaneously and runs locally on a MacBook Pro M4 Max or better; Block released demo recordings, opened a public waitlist, and offered early access to a small group of AI safety researchers.

Go to source

Bones