Show HN: Real-time local TTS (31M params, 5.6x CPU, voice cloning, ONNX)(github.com/ZDisket)
4 points by ZDisket 3 days ago | 4 comments
- chenglin97 3 days agoDoes it support other languages than English? I’m Chinese speaker[-]
- ZDisket 2 days agoNo multilingual capabilities yet, although that is planned for next iteration.
- popalchemist 3 days agogiven the architecture, is there a way to force the use of specific phonemes for hard-to-pronounce words? If so that's big[-]
- ZDisket 2 days agoYes. Specifically, the pipeline is text -> phonemizer -> phonemized text -> TTS model -> audio You just have to modify the phonemizer's dictionary.
- adriencr81 3 days ago[dead]