Underdog shows off a 32MB speech model in new demo
- ID
- 43769
- Status
- summarized
- Published
- 06 Nov 2026, 9:02 PM
- Fetched
- 06 Nov 2026, 9:30 PM
- Provider
- TechCrunch
- Category
- technology
- Original URL
- https://techcrunch.com/2026/11/06/underdog-shows-off-a-32mb-speech-model-in-new-demo/
- Source URL
- https://techcrunch.com/feed/
Summary
- Score
- 5.5
- Created
- 06 Nov 2026, 9:30 PM
- Tags
- Audience
- developersvibe_codersai_ml_learnersai_agent_users
What happened
Underdog released a browser game demo built around Woof, a text-to-speech model it says is 31.7MB with 31 million parameters and can run on most devices without an internet connection. In the demo, users type into a retro typewriter and hear the text spoken, and rotate a tuner to generate music; the model is open for download. It follows Underdog's 167MB Bark speech-to-text model for edge devices, and founder Sigil Wen said he built the demo to avoid cloud notetakers and keep data on users' devices.
Why it matters
If the 31.7MB claim holds, builders can prototype offline browser voice features—typed-to-speech, local assistant replies, game audio—without a cloud TTS API. But the demo does not provide quality, latency, or license details, so treat Woof as a test candidate, not a production replacement.
Discussion angle
What would you test first before using a 31.7MB browser TTS model in an agent: offline latency, pronunciation, license, or voice quality—and where does cloud TTS still win?