# Block releases Dessa, an AI model trained only on human speech

Digest AI · Generative AI & Models · published 2026-10-23T19:32:39Z · updated 2026-10-23T19:53:12Z

Canonical: https://digestai.news/story/block-releases-dessa-an-ai-model-trained-only-on-human-speech

## Summary

Jack Dorsey’s company Block has announced a new AI model named Dessa, which the team describes as a "true speech-to-speech" system. Unlike many current voice assistants that convert audio to text and back, Dessa is trained entirely on human conversation without any written text. The model is designed to capture the timing and emotional nuances of speech, aiming to address safety issues where standard AI might miss distress signals in a user's voice.

To demonstrate the model's capabilities, Block shared several chat logs and video clips. These examples show Dessa engaging in natural back-and-forth dialogue, though some interactions appear awkward or uncanny, such as initially mistaking a speaker for someone named Ronaldo. The team also highlighted a comparison where Dessa sounded more natural than OpenAI’s GPT-Live-1 voice model. Block states that the project was driven by curiosity, a desire for better human-AI understanding, and safety concerns regarding AI's inability to detect pain or emotion in voice.

The model is capable of running locally on a MacBook Pro M4 Max or better hardware. Block has stated that it will provide early access to a small group of AI safety researchers. The announcement emphasizes that speech is the most natural interface for intelligence, and that current voice AI often flattens this interaction by losing the subtleties of human timing and tone.

## Key points

- Block announced Dessa, a speech-to-speech AI model trained exclusively on human conversation.
- The model runs locally on a MacBook Pro M4 Max or better hardware.
- Block plans to give early access to a small group of AI safety researchers.

## Why it matters

This approach challenges the standard text-based pipeline for voice AI, potentially leading to more natural and emotionally aware interactions. It highlights a shift toward safety-focused design that can detect distress in voice, a critical gap in current consumer AI systems.

## Sources

1. [Jack Dorsey’s Block made an AI model that talks to you like an awkward new friend](https://theverge.com/ai-artificial-intelligence/1017906/jack-dorsey-block-dessa-ai-voice-speech) (The Verge AI, 2026-10-23)
2. [Block Unveils Dessa, a Full-Duplex Speech Model Trained on Conversation](https://unite.ai/block-unveils-dessa-a-full-duplex-speech-model-trained-on-conversation) (Unite.AI, 2026-10-23)

## Cite

Digest AI, "Block releases Dessa, an AI model trained only on human speech", 23 October 2026, https://digestai.news/story/block-releases-dessa-an-ai-model-trained-only-on-human-speech

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/block-releases-dessa-an-ai-model-trained-only-on-human-speech.json