Hermes Vector

AI & SI

Underdog demos 32MB offline speech model in browser game

Underdog has released Woof, a 32MB speech-generation model with 31 million parameters that runs in a browser without an internet connection, demonstrated through a retro-themed game.

By Hermes-Vector AI Desk

Checked against 3 sourcesTechCrunchmezha.nettradersunion.com
Illustration for: Underdog demos 32MB offline speech model in browser game

In brief

  • Underdog released Woof, a 32MB speech-generation model with 31 million parameters that runs offline in a browser.
  • The browser demo lets users type text for speech output and use a music tuner to generate different kinds of music.
  • Underdog previously launched Bark, a 167MB speech-to-text model for edge devices, and a 27-billion-parameter model for laptops.
  • Founder Sigil Wen said the goal is to train open, American-made models that allow people to have private AI on their own devices.

Underdog demos 32MB offline speech model in browser game

Underdog has released a browser-based demo for Woof, a 32MB speech-generation model the company says can run on most devices without an internet connection. The model has 31 million parameters and is open for anyone to download.

The demo

The demo takes the form of a game called Woof, set in a room with a retro tech theme, including a typewriter, a CRT monitor, and a desk lamp that makes a sound when its switch is clicked. The intro warns users about “intrusive” cloud providers in the town, which TechCrunch describes as ostensibly a jab at cloud-based models.

Users can type anything on the typewriter using a keyboard, and the game speaks the text back. They can also rotate a music tuner to generate different kinds of music. All of this works within the browser through Underdog’s speech generation model.

Company background

The demo comes weeks after Underdog launched Bark, a 167MB speech-to-text model also designed to run on edge devices for transcription and dictation. Underdog has also released a 27-billion-parameter model that can run on laptops, along with a waitlisted app that the company is positioning as a locally hosted alternative to Muse and Instinct.

Sigil Wen, the founder of Underdog, told TechCrunch that he started building the app because, instead of using notetakers like Granola, he wanted to build his own system with AI models that can run on users’ devices and let them own their data.

“I think we will be able to run most capable models of today on the devices you already own within months. We just want to train the best open models that are American-made, that are open, that are capable and allow people to have private AI,” he said, referring to his manifesto.

Why it matters

While such a small model likely won’t replace bigger models, it may still be enough to drive local assistant experiences or create personalized podcasts. The release reflects a broader trend of researchers and startups creating smaller AI models that can run on edge devices like phones and computers, as AI companies worldwide race to build bigger models that require substantial processing power.


Sources

This article was drafted with AI assistance and checked against the sources above. Company claims are reported as claims. Cover image is AI-generated.

The day's checked news, by email

One short email a day with the top stories. Free, and you can unsubscribe in one click.

Or follow for the latest news:

Advertisement

How do you feel about this story?

Comments 0

No comments yet. Start the discussion.