Kokoro Speaker in ComfyUI: Local Text-to-Speech Workflow
Generate natural, customizable AI voice audio locally using the open-source Kokoro Speaker workflow in ComfyUI.
About This Workflow
Convert written text into natural-sounding speech directly inside ComfyUI using a local text-to-speech workflow.
Create voiceovers for AI videos, tutorials, stories, and presentations without using any cloud services.
Generate different voice styles and tones, or combine multiple speakers to create unique custom voices.
Produce long audio outputs smoothly, making it suitable for narrations, audiobooks, and storytelling projects.
Run everything locally on your system, ensuring full privacy, faster generation, and zero API costs.
Workflow Graph
Read-only preview — Use the expand button for a larger view
Ready to use this workflow? Download the JSON file below — free, no signup needed.
Join the discussion
Sign in to leave a comment or reply
No comments yet
Be the first to share your thoughts!