tarasovcode
Models1 min readTechCrunch AI

Underdog shows off a 32MB speech model in new demo

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

Save
Share:VKTelegramWhatsApp
Underdog shows off a 32MB speech model in new demo
Illustration: Tarasov Code

In brief

  • What: Underdog shows off a 32MB speech model in new demo
  • When: November 6, 2026 at 16:02
  • Source: TechCrunch AI (media)
  • Topic: Models

#Models

Prepared by Ilya Tarasov’s Tarasov Code newsroom based on a report by TechCrunch AI.

Read next

MarkTechPost · November 6, 2026Thinking Machines Releases Inkling 2 Small, a 594B MoE With 17B ActiveWired AI · November 6, 2026Ads in Chatbots Have Arrived. Here’s What’s Working—and What’s NotMarkTechPost · November 6, 2026Baidu Releases ERNIE 5.5 Flash Base: A 280B MoE Base Model With 14B Active ParametersHugging Face · November 5, 2026New NVIDIA Cosmos 3 Open Models for Interactive World Simulation