PowerBeef

PowerBeef / QwenVoice

Public

Native macOS app for Qwen3-TTS — voice cloning, emotion control, and voice design, 100% offline on Apple Silicon

qwenvoice.vercel.app apple-silicon macos mlx native qwen
26
0
100% credibility
Found Mar 04, 2026 at 26 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Swift
AI Summary

QwenVoice is a native macOS app providing offline text-to-speech with custom voices, voice design from descriptions, and voice cloning from short audio clips using optimized models for Apple Silicon.

How It Works

1
📱 Discover QwenVoice

You find this free Mac app that turns text into speech with custom voices and cloning from short audio clips.

2
⬇️ Download and install

Download the app file, drag it to your Applications folder, and open it safely.

3
⚙️ App sets up automatically

The app prepares everything in the background so you can start creating voices right away.

4
🎵 Download a voice model

Pick a voice style like Custom Voice or Cloning, tap download, and watch it grab the files with a progress bar.

5
✨ Create your voice

Choose a speaker or upload a short clip to clone, type your text, and hit generate.

🎉 Hear your custom voice

Enjoy the generated speech playing back, save it to history, and use it anytime offline on your Mac.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 26 to 26 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is QwenVoice?

QwenVoice is a native macOS app that runs Qwen3-TTS models 100% offline on Apple Silicon for text-to-speech with voice cloning from 5-10s clips, voice design via natural language prompts like "deep narrator," and emotion control without sliders. Built in Swift with a bundled Python backend using Apple's MLX framework, it delivers fast inference, model downloads from Hugging Face inside the app, generation history, batch mode, and a CLI companion—all zero dependencies for users.

Why is it gaining traction?

It skips cloud APIs and Python setups entirely, bundling everything into a native macOS app that runs cool and quick on M-series chips. Natural language drives voice tweaks and emotions, waveform previews play instantly, and Finder integration reveals outputs fast. Devs dig the offline privacy and speed over browser-based or server-dependent TTS tools.

Who should use this?

Mac app devs prototyping voice features, podcasters cloning guest voices offline, or AI tinkerers needing local TTS for scripts without latency. Ideal for remote desktop macOS native workflows or native macOS games adding dynamic narration.

Verdict

Grab it for Apple Silicon TTS experiments—promising native macOS version with UI tests and benchmarks, but 26 stars and 1.0% credibility score mean alpha risks like macOS 14+ limits. Watch this github native ui project; enable automerge in repo settings for smoother contribs.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.