# Block's New Voice Model Sounds Eerily Human

> **Platform:** [SPIDITS AI](https://spidits.com/) — Real-Time AI News & Market Intelligence  
> **Published:** 2026-10-24T12:00:00.000Z  
> **Category:** PRODUCT_LAUNCH  
> **Impact Score:** 90/100  
> **Primary Source:** [TechCrunch AI](https://techcrunch.com/2026/10/24/blocks-new-voice-model-sounds-eerily-human)  
> **Canonical Citation:** [https://spidits.com/timeline/block-s-new-voice-model-sounds-eerily-human](https://spidits.com/timeline/block-s-new-voice-model-sounds-eerily-human)

## Executive Summary
Block said that the voice model can run locally on a MacBook M4 Max.

## Why It Matters (Strategic Analysis)
Eliminating the text intermediate step in speech synthesis architectures bypasses the information loss inherent in traditional text-to-speech pipelines, allowing for direct emotional and conversational fidelity. Enabling full-duplex local execution on consumer hardware reduces reliance on centralized cloud APIs and redefines latency expectations for real-time voice agents.

## Referenced Coverage & Sources
- **[TechCrunch AI](https://techcrunch.com/2026/10/24/blocks-new-voice-model-sounds-eerily-human)**: Block's new voice model sounds eerily human — _Typically, speech models are paired with a large language model for knowledge retrieval. Block said that Dessa's knowledge stems from the conversational data..._

---
*Synthesized by SPIDITS AI Market Intelligence Desk. Track live AI news, model releases, and funding: [https://spidits.com](https://spidits.com)*