Dessa

Dessa is a full-duplex speech model released by Block as a research preview in 2026 that generates conversational speech directly without an intermediate text step.

1 articleLast mentioned

Dessa is a conversational speech model developed by Block. Released as a research preview in 2026, it generates speech directly, having been trained from the start on recordings of real human conversation, instead of using the common three-stage pipeline of speech recognition, text processing by a language model and text-to-speech synthesis. It operates in full-duplex mode, listening and speaking at the same time, which lets it reproduce interruptions, conversational timing and non-verbal sounds such as laughter and breathing.

The name comes from Dessa, a Toronto machine learning company that Block (then Square) acquired in 2020.

This entry is based on AIPOST articles and widely known facts. If something is wrong, please send us a correction request.

Articles covering this entry

  • GPT-6.1 Terra, Dot Texting and Gemini 4 Carbon: What Works Now and What WaitsAI News ·

    Preview only: Gemini 4 Carbon and the Dessa voice model

    Read article

Found a mistake or missing an entry?

Wiki entries are based on AIPOST articles and widely known facts. If an entry is wrong, send us a correction request and we will check and fix it. Names from new articles are added to the wiki after the article is published.