The Local Lab

ComfyUI-F5-TTS node allows direct use of F5 TTS models within ComfyUI. It performs well on low VRAM devices - I was able to generate audio smoothly and quickly even with my RTX 4050 6GB VRAM and 16 GB RAM PC. I have a video tutorial below if needed: <a href="https://youtu.be/seOIKqOyB6M" target="_blank">https://youtu.be/seOIKqOyB6M</a> <div data-w-e-type="video" data-w-e-is-void>
<video poster="" controls="true" width="auto" height="auto"><source src="https://youtu.be/seOIKqOyB6M" type="video/mp4"/></video>
</div>

OpenArt

Workflows

Active Sessions

F5 TTS Voice Cloning in ComfyUI

Description

Discussion

Loading...