VoiceStudio Use the user's running VoiceStudio backend. Prefer local processing; cloud translation, model downloads, remote-backend connections, and external integrations require the user's choice. Installed models can run offline; do not promise that every configured workflow is offline. Connect and discover The default backend is ; honor the user's configured address. Electron's renderer and development proxy are separate services, not the public backend API. 1. Check . 2. Discover the running version's contracts with , and voices/engines with . Do not invent profile IDs or infer installed…