Underdog shows off a 32MB speech model in new demo

Practical AI: Tools, Models & Frameworksnew model

What changed

AI companies across the world are racing to make bigger and better models, but the problem is all of them need massive amounts of processing power. One such startup, Underdog, has released a game built with its new voice model called Woof that’s only 32MB large. This demo comes weeks after Underdog launched Bark, a 167 MB speech-to-text model also designed to run on edge devices for transcription and dictation.

Why it matters

A concrete addition to Practical AI: Tools, Models & Frameworks: it changes what's available to builders today rather than being general commentary.

How it compares

Related prior coverage to compare against:

  • Introducing the Realtime API
  • Introducing gpt-realtime and Realtime API updates
  • Measuring benchmark optimization in speech recognition

Sources