ComfyUI Course - Learn ComfyUI From Scratch | Pixaroma - How to Use Fish Audio S2 Text to Speech in ComfyUI (Ep10)

Learn how to install, set up, and use the Fish Audio S2 Text-to-Speech model in ComfyUI, including fixes for common errors, model selection, and voice cloning workflows. This tutorial shows how to generate natural speech, use tags for emotion and style, and work with multi-speaker outputs. In this tutorial, you’ll learn: - How to install Fish Audio S2 using Easy Installer or manual setup - How to fix “model not in list” and startup errors in ComfyUI - How to download and select the correct model (FP8 vs auto-download) - How to generate speech with tags, seeds, and language settings - How to clone voices using reference audio and transcripts - How to create multi-speaker dialogue workflows --- Workflows download links (Discord, GitHub Releases): https://github.com/pixaroma/pixaroma-workflows --- Run ComfyUI in the Cloud RunComfy: https://www.runcomfy.com/?ref=ioan RunningHub: https://www.runninghub.ai/?inviteCode=kol02-rh003 --- Thanks for support: https://craftopia-studio.com Playlist where I add all the episodes https://www.youtube.com/playlist?list=PL-pohOSaL8P-FhSw1Iwf0pBGzXdtv4DZC 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 --- #comfyui #comfyuitutorial