Well all, its a bit endless.. this is a hard task since few of the new players (11labs, PlayHT) bother with SSML or word timings.. but you know, we try and deal with workarounds. Feel free to get on board if TTS is your thing..

Am I misunderstanding the purpose, or did they forget Coqui/MozillaTTS?

Coqui works using Sherpa onnx.

You could add in MacOS built in "say" command line utility.

fyi we currently support macos with systemtts (so sapi on windows and nss on Mac). But I really need to build a new replacement as nsss is deprecated.. nb: our engine does more than say - we do word events and standardise languages/calls etc

anyone konws good offline tts engine which can support multi-language like English and Chinese?

sherpa-onnx. use one of these models - https://k2-fsa.github.io/sherpa/onnx/tts/pretrained_models/r... - if you use py3-tts-wrapper you can get a list of these using the get_voices method