---
title: "Block unveils Dessa, a speech model that runs locally on a MacBook"
url: https://www.parallelquant.com/posts/block-unveils-dessa-a-speech-model-that-runs-locally-on-a-macbook-3dceb4
source_name: "The Decoder"
source_url: https://the-decoder.com/blocks-new-ai-model-dessa-was-trained-entirely-on-human-speech-to-catch-emotions-text-based-models-miss/
published: 2026-10-24T14:09:46.000Z
topics: ["llms", "products"]
publisher: "Parallel Quant"
---

# Block unveils Dessa, a speech model that runs locally on a MacBook

*2026-10-24 · Source: [The Decoder](https://the-decoder.com/blocks-new-ai-model-dessa-was-trained-entirely-on-human-speech-to-catch-emotions-text-based-models-miss/)*

Block, the company behind Square and Cash App, introduced Dessa, a model that processes audio directly instead of transcribing it to text first. It is designed to recognize emotion, sarcasm and pauses in real time. It runs locally on a MacBook Pro M4 Max but is not publicly available yet.

**Why it matters:** Native speech models that skip the text step can keep tone and timing that transcription discards, which matters for voice agents. Running on a laptop fits the recent push toward small local voice models, such as NVIDIA's Nemotron Bolt, and a fintech company building one suggests customer-facing voice is a competitive area.

**Topics:** llms, products

---
Read the original: https://the-decoder.com/blocks-new-ai-model-dessa-was-trained-entirely-on-human-speech-to-catch-emotions-text-based-models-miss/
Canonical: https://www.parallelquant.com/posts/block-unveils-dessa-a-speech-model-that-runs-locally-on-a-macbook-3dceb4
Published by Parallel Quant — https://www.parallelquant.com