Underdog releases 32 MB speech model for offline browser use

Underdog's new speech model is 32 MB (31 M parameters) and runs fully offline in browsers, powering the Woof demo game that speaks typed text and generates music. The model is open‑source and downloadable for edge devices.

Benchmarks are the company's own; not independently verified.

Why it matters

Underdog's 32 MB, 31 M‑parameter speech model enables offline assistants; consider building local voice features to meet edge expectations.

For product managers

For your product

What does this mean for your product?

Try it on your product

Read at TechCrunch

More from this issueAll AI news from 7 Nov →

Thinking Machines Lab releases Inkling 2 Small 594B MoE with 17B activeAvailable now

OpenAI valued at $1.25 trillion after $11 billion funding round

Amazon launches text‑based Alexa shopping assistant for US customersAnnounced

Ricursive Intelligence releases Ripple-65B Preview, tops open US models on TerminalBenchAvailable now

Get this every morning, written for your product.

Deltaday reads the whole AI news cycle and tells you what changed, whether it's real yet, and what to do about it.

Start free See how it works

Underdog releases 32 MB speech model for offline browser use

Get this every morning, written for your product.

Underdog releases 32 MB speech model for offline browser use