TTS
A latent audio encoder has a small-looking job. audio -> encoder -> latent -> decoder -> audio If the goal is compression, this sketch is almost enough. The encoder should make the middle object small, and the decoder should reconstruct the signal. Most modern continuous audio
TTS
Text-to-speech used to be easy to sketch. text -> acoustic model -> vocoder -> waveform That sketch still describes many good systems. It also hides most of what has changed. The newer TTS papers are not just swapping one Transformer for another. They are choosing different objects
TTS
MOSS-TTS turns each speech frame into an ordered RVQ stack. The interesting question is how much compute and memory each residual depth band deserves.
TTS
Suppose we only want a text-to-speech system to speak one sentence. It needs to know the words. It needs a speaker voice. It needs to turn those things into audio. This is already hard, but the shape of the problem is still pretty small. Now ask for something more like