Qwen3-TTS: The New King of Open Source Text-to-Speech? (Voice Design, Cloning & More!)



Is Qwen3-TTS the New King of Open Source Text-to-Speech?

In this video, I'll show you how to use Qwen3-TTS, the powerful open-source model from the Alibaba group.

We are running this entirely locally on a Windows PC using Pinokio, so your data stays private and your generations are free.

In this video, you will learn:

1. How to set up Qwen3-TTS using Pinokio.

2. How to load models into your GPU and monitor VRAM usage.

3. Voice Design: Creating unique AI characters (like an elderly wizard!) using just text descriptions.

4. Voice Cloning: How to upload a sample and clone any voice in seconds.

5. Custom Voice: Using preset speaker profiles with instruction-based acting notes.

Get the latest episodes directly in your inbox