From CLI to GUI: Building an AI Podcast Studio (PodVoice)

I originally built PodVoice as a CLI tool to convert Markdown into multi-speaker audio using Coqui XTTS. While it worked well, usability was a challenge. So I built PodVoice Studio — a web-based GUI on top of it. Key features: Voice gallery with preview Single & multi-speaker generation Markdown-based scripting Fully local execution Tech stack: Python FastAPI Coqui XTTS Would love feedback from the community. GitHub: https://github.com/aman179102/podvoice