What do you think about TTS WebUI?
Single Gradio + React web interface supporting 20+ text-to-speech and audio generation models. Includes ACE-Step, Kimi Audio, Piper TTS, GPT-SoVITS, CosyVoice, XTTSv2, DIA, Kokoro, OpenVoice, ParlerTTS, Stable Audio, MusicGen, Tortoise, and more. MIT licensed with 3K GitHub stars.
