---
title: "Underdog shows off a 32MB speech model in new demo"
source: "TechCrunch：AI（RSS）"
source_tier: "t2"
url: "https://techcrunch.com/2026/11/06/underdog-shows-off-a-32mb-speech-model-in-new-demo/"
permalink: "https://feed.astralor.com/items/itm_a394d9aad7a2ef1699f9615a"
published: "2026-11-06T13:02:16.000Z"
score: 54
channel: "ai"
tags: ["Underdog","Despite"]
---

# Underdog shows off a 32MB speech model in new demo

## At a glance

Despite its small size, Underdog's new model can generate both speech and music.

## Key points

- Despite its small size, Underdog's new model can generate both speech and music.

## Full text

Despite its small size, Underdog's new model can generate both speech and music.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_a394d9aad7a2ef1699f9615a