Underdog Woof TTS — 1-click Pinokio launcher 🐶
Underdog Woof is a tiny English text-to-speech model from Conway Research. This launcher runs it on your own machine
in one click, and no GPU is needed.
🪶 The whole model is one 40.6 MB file (38M parameters)
💻 Runs on CPU using only numpy. No PyTorch, no CUDA
🎙️ Two voices: Juno and Mira
🔢 It reads numbers, dates, times, prices and codes the way people say them ("415-555-0199", "5:30 p.m.", "March 3rd")
🎲 Temperature and seed controls: the same text and seed always give the same audio
💾 Every clip is saved as a 24 kHz WAV (Outputs button in the sidebar)
🔌 Comes with an API, with Python, JavaScript and curl examples in the README
Install → Start → Open Web UI. That's it.
Model: huggingface.co/ConwayResearch/U…
Try it in your browser first: underdog.ai/woof
Launcher: github.com/PierrunoYT/Underdog-…
⚠️ The model is non-commercial (Underdog Non-Commercial License 1.0). Credit it as "Voice by Underdog Woof".
#texttospeech
Browse tags
Most posts · Last 30 days
No recent tagged posts yet.
You’re all caught up.
Join the community
Follow people and apps for updates. Explore Announcements and All for more.
Discover people →
