ComfyUI Tutorial Series Ep 65: VibeVoice Free Text to Speech Workflow

Sobre esta lección

Learn how to use VibeVoice, a free text-to-speech (TTS) node in ComfyUI, to clone voices and generate realistic AI speech directly from text. In this episode, we’ll walk through the VibeVoice setup, model installation, and workflow configuration so you can start creating your own AI-generated voiceovers with ease. You’ll see how to: - Install the VibeVoice ComfyUI node using the Custom Node Manager - Download and organize the tokenizer and model files (for both 1.5B and Q8 versions) - Configure your audio workflow with the Load Audio, VibeVoice, and Save Audio nodes - Test single and multi-speaker voice cloning - Troubleshoot common generation issues like glitches or slow output Whether you’re making AI voiceovers for videos, tutorials, or creative projects, this guide shows how to get speech synthesis for free using ComfyUI. Get the workflows and instructions from discord for free Step 1: use this link to join if you didn't join already https://discord.gg/gggpkVgBf3 Step 2: go to this post to get the workflows https://discord.com/channels/1245221993746399232/1425151091301158973/1425151349049524316 Node Used https://github.com/Enemyx-net/VibeVoice-ComfyUI Tokenizer files https://huggingface.co/Qwen/Qwen2.5-1.5B/tree/main VibeVoice 1.5B Model https://huggingface.co/microsoft/VibeVoice-1.5B/tree/main VibeVoice Q8 Model https://huggingface.co/FabioSarracino/VibeVoice-Large-Q8/tree/main Check Other Episodes https://www.youtube.com/playlist?list=PL-pohOSaL8P9kLZP8tQ1K1QWdZEgwiBM0 Unlock exclusive perks by joining our channel: https://www.youtube.com/channel/UCmMbwA-s3GZDKVzGZ-kPwaQ/join Grab your Pixaroma merch from here: https://www.youtube.com/@pixaroma/store