I'm really surprised how clean and simple the app works. Normally I'm someone that uses almost only Open Source Apps because I like seeing the source code, but wow it's really simple and clean to use. Only thing missing would be native Qwen3-TTS support, this TTS model is like made for things like this.
Viewing post in Desktop Companion - Your AI Desktop Pal comments
Thank you! I actually spent quite a bit of time trying to implement Qwen3-TTS (which is genuinely impressive), but it requires a high-end NVIDIA GPU to achieve acceptable latency for real-time usage — on CPU, it takes around 30 seconds to generate just 3 seconds of audio. I'll hold off on adding it until a DirectML streaming solution becomes available.