Fish Audio para Locução e voz com IA

Opiniões da comunidade

• 2026-09-14T01:50:03.117369+00:00 — RGS1811

  I've got the best results with BreezeTTS, Higgs Audio v3, and Fish Audio S2 Pro. audio.cpp ( ) is an easy way to run a lot of different models. Different models have different strengths. If you throw an entire ebook at a model you're going to get a different result than if you craft a perfect 10 second sentence with a model that supports voice direction and emotion tags, so you should try a bunch depending on your use case.

• 2026-07-14T21:57:44.49711+00:00 — JayceAllanGuitar

  I just got fish audio working on amd. I'm on linux though, but if anyone's interested I can write down how I did it later. Speed is really fast on a 9070, ~100-110it/s (their wiki says an rtx 4090 is 150it/s, comparably). Multiple times real time, even voice cloning works.