Can't get TTS to work ?
I'm new to ai voices, still managed to run this : https://github.com/JarodMica/ai-voice-cloning
But it seems i don't know how to use the files for TTS, it says "Unsupported audio format provided: .pth".
If anyone can help me, i already found topics speaking about this format issue but no explanations, just someone who got his problem fixed without explaining how (https://github.com/JarodMica/ai-voice-cloning/discussions/8) or something that straight up don't work (https://git.ecker.tech/mrq/ai-voice-cloning/issues/466)
Hi
This particular project is a voice-to-voice model for the AI tool called RVCv2, or "Retrieval-based Voice Conversion".
Personally, I use this tool.
It seems the tool you are using "AI voice cloning" can do RVC, and they say that "Before you can use it, you will need a trained RVC .pth file that you get from RVC or online, and then you will need to place it in models/rvc_models/".
From the error you get (Unsupported audio format provided: .pth), it seems you are instead trying to use the .pth file as an audio file. You need to generate an audio file first using TTS (from another model). My model only does audio-to-audio/voice-to-voice conversion. Feel free to reply here in case you need more help.