Post
69
I made a small English text-to-speech model called tiny-voca. It has 4.5M parameters, two voices, and it runs in your browser.
Try it here, nothing is sent to a server: https://tiny-voca.n4ze3m.com
Some facts:
- 4,537,291 parameters, 18 MB. This is the whole model, the waveform part is included.
- Two voices, one female and one male. 24 kHz.
- About 70x faster than real time on 4 CPU threads.
- Runs with PyTorch, ONNX, and in the browser.
- Trained from scratch in 7.7 hours on one RTX 4090.
What I think is different:
- Everything is open. Code, weights, the training recipe and the dataset.
- Custom phonemizer.
- No neural vocoder. The sound is made by a small source-filter synth, which is why it is fast.
What is not good yet:
- English only, and only these two voices. No voice cloning.
- Foreign names and odd spellings are often read wrong.
- It can sound a bit synthetic.
- The training audio is synthetic too. I made it with Qwen3-TTS, so the model can't sound better than that.
Links:
- Demo: https://tiny-voca.n4ze3m.com
- Code: https://github.com/n4ze3m/tiny-voca
- Weights: n4ze3m/tiny-voca
- Dataset: n4ze3m/tiny-voca
- Phonemizer: https://github.com/n4ze3m/dizione
Try it here, nothing is sent to a server: https://tiny-voca.n4ze3m.com
Some facts:
- 4,537,291 parameters, 18 MB. This is the whole model, the waveform part is included.
- Two voices, one female and one male. 24 kHz.
- About 70x faster than real time on 4 CPU threads.
- Runs with PyTorch, ONNX, and in the browser.
- Trained from scratch in 7.7 hours on one RTX 4090.
What I think is different:
- Everything is open. Code, weights, the training recipe and the dataset.
- Custom phonemizer.
- No neural vocoder. The sound is made by a small source-filter synth, which is why it is fast.
What is not good yet:
- English only, and only these two voices. No voice cloning.
- Foreign names and odd spellings are often read wrong.
- It can sound a bit synthetic.
- The training audio is synthetic too. I made it with Qwen3-TTS, so the model can't sound better than that.
Links:
- Demo: https://tiny-voca.n4ze3m.com
- Code: https://github.com/n4ze3m/tiny-voca
- Weights: n4ze3m/tiny-voca
- Dataset: n4ze3m/tiny-voca
- Phonemizer: https://github.com/n4ze3m/dizione
