I’m trying to do voice cloning for animations/lip-syncs. By now fast-tts is doing the job but the results aren’t always usable. Sometimes it switches gender, it’s kinda metallic and it’s very slow and i’m tired of python requirements… I’ve tried non-locals like Murf.ai, natural-reader and 11labs but the least disabled voice-cloning for free users and i just don’t want to submit my credit-card details cause of their privacy policy. Now i’m left wondering if i just wait for the opensource community to enhance or to swallow the bitter pill and register with 11labs. Has anyone experience with TTS?