# Underdog-Woof

> Underdog Woof is a small English text-to-speech model with two voices: Juno and Mira. It reads phone numbers, dates, prices and codes the way people say them, and it runs on a laptop CPU with nothing but numpy, from a single 40.6 MB file. Try it in your browser at underdog.ai/woof.

- **Organisation:** ConwayResearch
- **Category:** Text-to-Speech
- **Licence:** underdog-non-commercial-1.0 (Non-commercial)
- **Released:** 2026-11-05
- **Hugging Face:** 10 downloads (30 days), 267 likes

## About

Underdog Woof is a small English text-to-speech model with two voices: Juno and Mira. It reads phone numbers, dates, prices and codes the way people say them, and it runs on a laptop CPU with nothing but numpy, from a single 40.6 MB file. Try it in your browser at underdog.ai/woof.

Each voice reads "Please call me back at 415-555-0199 before 5:30 p.m. on Friday." (seed 1).

More clips are in the samples folder, listed below.

Woof comes in two sizes. This repo is the two-voice model. The one-voice model is the one that runs in your browser at underdog.ai/woof.

The one-voice speed is plain PyTorch with its int8 weights at the default 16 steps; the two-voice speed is this repo's numpy runtime. Fish Audio Drama 3, for scale, is a 41.5 GB download and gets 1.89% wrong.

Word error rate on Gradium TTS Hard Cases (English, 500 sentences), every model run and scored by us the same way, each in its best-scoring voice. Lower is better.

Kitten Nano 0.8 is the only smaller download, and it gets 9.81% of words wrong: nothing we tested is both smaller and more accurate than Woof. Transcripts by qwen3.8-omni-flash, word errors counted by gemma-4-31b-it. Download is the smallest official set of weights each model needs to run, from its Hugging Face repo in November 2026 (Phonon 31m: the 4-bit GGUF; Kitten Nano: the int8 ONNX plus voices; Pocket TTS: the English model; Qwen3-TTS: the model plus its speech tokenizer). Cloud-only models don't publish a size.

## Alternatives

- [k2-fsa/OmniVoice](https://selfhost.directory/models/k2-fsa/omnivoice) (613M, Unknown licence, ≈1.87 GB): OmniVoice is a massively multilingual zero-shot text-to-speech (TTS) model supporting over 600 languages. Built on a novel diffusion language model-style architecture, it delivers high-quality speech with superior inference speed, supporting voice cloning and voice design.
- [openbmb/VoxCPM2](https://selfhost.directory/models/openbmb/voxcpm2) (2.3B, Apache 2.0, ≈5.62 GB): VoxCPM2 is a tokenizer-free, diffusion autoregressive Text-to-Speech model — 2B parameters, 30 languages, 48kHz audio output, trained on over 2 million hours of multilingual speech data.
- [Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice](https://selfhost.directory/models/qwen/qwen3-tts-12hz-1.7b-customvoice) (1.9B, Apache 2.0, ≈4.78 GB): Qwen3-TTS covers 10 major languages (Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian) as well as multiple dialectal voice profiles to meet global application needs.
- [Qwen/Qwen3-TTS-12Hz-0.6B-Base](https://selfhost.directory/models/qwen/qwen3-tts-12hz-0.6b-base) (915M, Apache 2.0, ≈2.54 GB): Qwen3-TTS is a family of advanced multilingual, controllable, robust, and streaming text-to-speech models. Trained on over 5 million hours of speech data spanning 10 languages, Qwen3-TTS supports state-of-the-art 3-second voice cloning and description-based control.
- [hexgrad/Kokoro-82M](https://selfhost.directory/models/hexgrad/kokoro-82m) (82M, Apache 2.0, ≈0.68 GB): Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient.
- [Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice](https://selfhost.directory/models/qwen/qwen3-tts-12hz-0.6b-customvoice) (906M, Apache 2.0, ≈2.52 GB): Qwen3-TTS is a series of advanced multilingual, controllable, robust, and streaming text-to-speech models developed by the Qwen team.

More: https://selfhost.directory/models/conwayresearch/underdog-woof/alternatives

## FAQ

**Can I use Underdog-Woof commercially?**
No. It is released under underdog-non-commercial-1.0. Custom licence: read the model card before using it commercially.

## Links

- huggingface: https://huggingface.co/ConwayResearch/Underdog-Woof

---
Source: https://selfhost.directory/models/conwayresearch/underdog-woof