Hacker News Reader

Slightly disappointed this is for recognition, not for synthesis (and not open source).

Is there any good quality, open source multi-language TTS setup available? Flite works, but doesn't sound very good.

There are a lot of text-to-speech models on Hugging Face. Some are really great and support many languages! They can be run offline easily, you just need a GPU and some python modules. https://huggingface.co/models?pipeline_tag=text-to-speech

Another open source option is espeak[1], though it isn't substantially better than flite, in my experience.

[1] https://github.com/rhdunn/espeak

Reply on news.ycombinator.com