---
format: "aidr-story-markdown/v1"
id: "aa761416b31101fe82ff76e0ef7763523f12d573c41b1f1a64a3e18b5f88cec8"
canonical_url: "https://aidr.today/aa761416?lang=en"
title: "A 4.5M-parameter TTS model runs 70x real-time on CPU and cost just $10 to train"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-18T15:01:14.000Z"
category: "Models"
topics: ["inference"]
source_urls: ["https://huggingface.co/n4ze3m/tiny-voca","https://news.ycombinator.com/item?id=50547122"]
summary: "Text-to-Speech model. Download, explore files and run it on Hugging Face."
---

# A 4\.5M\-parameter TTS model runs 70x real\-time on CPU and cost just $10 to train

> [Open the canonical story](<https://aidr.today/aa761416?lang=en>)

**Published:** 2026-11-18T15:01:14.000Z
**Category:** Models
**Topics:** inference

## Summary

Text\-to\-Speech model\. Download, explore files and run it on Hugging Face\.

## Sources

- [Story source](<https://huggingface.co/n4ze3m/tiny-voca>)
- [Discussion](<https://news.ycombinator.com/item?id=50547122>)

