Underdog says Woof beats text-to-speech models 1,000x larger on word error rate while being small enough to run in a browser, phone or watch. It runs fully in WebGPU and keeps working offline, and the weights are free under a non-commercial CC BY-NC 4.0 li...
VQV Signal
OPEN SOURCE
WATCH
TECHNICAL
Underdog releases Woof, a 31.7 MB open-weight speech model
Underdog says Woof beats text-to-speech models 1,000x larger on word error rate while being small enough to run in a browser, phone or watch. It runs fully in WebGPU and keeps working offline, and the weights are free under a non-commercial CC BY-NC 4.0 li...
Underdog says Woof beats text-to-speech models 1,000x larger on word error rate while being small enough to run in a browser, phone or watch. It runs fully in WebGPU and keeps working offline, and the weights are free under a non-commercial CC BY-NC 4.0 license. Why it matters: Good on-device voice cuts cost and...
VQV organizes public signals from inspectable sources. It does not independently verify the underlying report.
Signal Strength 91%
Technical label WATCH
Public Interest 35
Category OPEN SOURCE
Reader Depth TECHNICAL
Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.
Public Interest components
Recognizable Entity Score 0
Practical Impact Score 26
Novelty Interest Score 94
Consequence Score 18
Curiosity Score 32
Shareability Score 50
Topics
VQV surfaced this signal because it is recent, relevant to AI Voice, connected to Scobleizer News Pulse (X).
No login, cookies, social SDKs, or automatic posting.