dovvnloading/Qwen3-TTS-1.7B

A desktop interface for the powerful Qwen3-TTS model (1.7B CustomVoice). Run offline, ultra-low latency text-to-speech with emotive control directly on your GPU.

31
/ 100
Emerging

This tool helps content creators, educators, and marketers generate high-quality, emotionally expressive voiceovers for their projects. You input text and natural language style instructions (e.g., "whispering and terrified"), and it outputs speech in one of nine premium voices across multiple languages. This is for anyone who needs realistic, nuanced spoken audio without relying on cloud-based services.

Use this if you need to create custom voiceovers for videos, presentations, or audiobooks with precise emotional control and privacy, running entirely on your own computer.

Not ideal if you don't have a dedicated NVIDIA GPU with at least 8GB VRAM, as it relies on local GPU processing for performance.

voiceover-production content-creation e-learning audio-narration digital-media
No License No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 3 / 25
Community 13 / 25

How are scores calculated?

Stars

9

Forks

2

Language

TypeScript

License

Last pushed

Mar 08, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/dovvnloading/Qwen3-TTS-1.7B"

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