gabriele-mastrapasqua/qwen3-tts

Pure C inference engine for Qwen3-TTS text-to-speech. No Python, no PyTorch — just C and BLAS. Supports 0.6B and 1.7B models, 9 voices, 10 languages.

47
/ 100
Emerging

This project helps you convert written text into natural-sounding speech for various applications. You provide text in one of ten languages and choose from nine preset voices, or even clone a voice from an audio clip, to generate an audio file. This tool is ideal for developers and system administrators who need to integrate high-quality text-to-speech capabilities directly into their applications or devices without complex dependencies.

Use this if you need a lightweight, high-performance text-to-speech engine that can run directly on various hardware, including embedded systems, without relying on Python or large machine learning frameworks.

Not ideal if you are looking for a user-friendly application with a graphical interface for personal content creation, or if you prefer a cloud-based text-to-speech service.

voice-synthesis audio-generation speech-engine embedded-systems localization
No Package No Dependents
Maintenance 13 / 25
Adoption 7 / 25
Maturity 11 / 25
Community 16 / 25

How are scores calculated?

Stars

25

Forks

6

Language

C

License

MIT

Last pushed

Mar 16, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/gabriele-mastrapasqua/qwen3-tts"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.