# Block's Dessa learns conversation from audio alone as Ollama adds local speech synthesis

Block trained the full-duplex model from scratch on recorded human conversation using a single GB200 NVL72 system, while Ollama now serves Gradium's Phonon voices more than 100 times faster than real time on Apple Silicon.

- Published: 2026-10-25T06:22:55.342Z
- Canonical: https://polylog.news/ai/2026-10-25/block-s-dessa-learns-conversation-from-audio-alone-as-ollama
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Polylog editors](https://polylog.news), [Ollama](https://ollama.com/blog/speech-models)

Block, the payments company led by Twitter co-founder Jack Dorsey, showed a conversational model called Dessa. It was trained only on recordings of human speech, without text and without a pretrained base model, AI ML Big Data reported. Blo…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-10-25/block-s-dessa-learns-conversation-from-audio-alone-as-ollama (subscription information: https://polylog.news/pricing).