# PiVo-1.4M: 1.4M-parameter English TTS that runs offline on CPU

> Original title: English TTS in just 1.4M parameters, vocoder included. PiVo-1.4M runs offline on a CPU with NumPy and ONNX Runtime, without PyTorch.

- Source: ModelScope
- Published: 2026-11-02T10:00:52.000Z
- Bad Influence: https://badinfluence.news/items/wxg61bgt9awdtaz66df0aqr62
- Original: https://x.com/ModelScope2022/status/2117195229203730936

## Summary

ModelScope releases PiVo-1.4M, an English text-to-speech model with 1.4M parameters and a built-in vocoder that generates 16 kHz mono speech. It runs offline on CPU using NumPy and ONNX Runtime without PyTorch, and reaches a 0.532% WER on its held-out test set, a measure of intelligibility rather than naturalness.

## Post

English TTS in just 1.4M parameters, vocoder included. PiVo-1.4M runs offline on a CPU with NumPy and ONNX Runtime, without PyTorch.
🤖 https://modelscope.ai/models/empero-ai/PiVo-1.4M

🪶 1.4M parameters, vocoder included: Generates 16 kHz mono speech with a compact acoustic model and FARGAN-derived vocoder.
🖥️ Built for local, offline use: Generate with either English voice, Pi or Vo, directly on CPU and begin playback in 10 ms audio frames after text encoding.
🗣️ Words come through clearly: PiVo reaches 0.532% WER on its held-out test set. The authors note that this measures intelligibility, not general English quality or naturalness.
🔤 Predictable English pronunciation: It expands numbers, currencies, ordinals, and ISO dates, while unsupported words raise a clear error instead of silently guessing.
📜 Code and acoustic weights are Apache-2.0. The FARGAN-derived vocoder uses Xiph/Opus BSD terms, and the pronunciation dictionary retains its CMU license.

[Video](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fext_tw_video_thumb%2F2117195222140567553%2Fpu%2Fimg%2FV5gjXXvOLgM7iMuF.jpg&mode=thumb&exp=1793836800&sig=35c4c8311fd9fdbf)