Clone of ANY voice and create a lip-synched animation with Tortoise-TTS and StableDiffusion

Render Realm · Beginner ·🎨 Image & Video AI ·2y ago
In this quick tutorial I will show you how to clone ANY voice and create a flicker-free, lip-synched animation of that person, using only free AI-tools (Tortoise-TTS, Stable Diffusion / Automatic1111/ SadTalker). Some useful links: ------------------------------ Download Audacity: https://www.audacityteam.org/download/ Google Colab link Tortoise-TTS: https://colab.research.google.com/drive/1N8lXviiwfmrS9vYzuFdQnLHlddXMMMvU#scrollTo=vF1d-My9IXXt Github-Link Tortoise: https://github.com/neonbjb/tortoise-tts Github Link SadTalker: https://github.com/OpenTalker/SadTalker Download SadTalker Che…
Watch on YouTube ↗ (saves to browser)
What is interpolation, really? | Dirty D3 - Episode 3
Next Up
What is interpolation, really? | Dirty D3 - Episode 3
Fun Fun Function