Show HN: Real-time local TTS (31M params, 5.6x CPU, voice cloning, ONNX)github.com4 points·by ZDisket·4 mesi fa·4 comments
ZDisket·4 mesi fa·discussYes. Specifically, the pipeline is text -> phonemizer -> phonemized text -> TTS model -> audio You just have to modify the phonemizer's dictionary.
ZDisket·4 mesi fa·discussNo multilingual capabilities yet, although that is planned for next iteration.
ZDisket·4 mesi fa·discussI'll explain in detail once I've got the big release, but everything's been thoroughly modernized. Transformer, HiFi-GAN (now iSTFTNet w/Snake) vocoder, et al, plus a few additions.
ZDisket·4 mesi fa·discussI'm working on a voice cloning version of my TTS model, a highly upgraded VITS:https://x.com/ZDi____/status/2013655958027669958Right now, I only have single speaker checkpoints (as per the old video). That will change soon.
ZDisket·4 mesi fa·discussUpwork has candidates buy "connects" with real money that are spent when applying to jobs. Ultimately it seems some form of payment is a proven gate.