There are people – and it does not matter what it's about – that will overstate the progress made (and others will understate it, case in point). Neither should put a damper on progress. This is the best I personally have heard so far, but I certainly might have missed something.
However Kokoro-82M is an absolute triumph in the small model space. It curbstomps models 10-20x its size in terms of quality while also being runnable on like, a Raspberry Pi. It’s the kind of thing I’m surprised even exists. Its downside is that it isn’t super expressive, but the af_heart voice is extremely clean, and Kokoro is way more reliable than other TTS models: It doesn’t have the common failure mode where you occasionally have a couple extra syllables thrown in because you picked a bad seed.
If you want something that can do convincing voice acting, either pay for ElevenLabs or keep waiting. If you’re trying to build a local AI assistant, Kokoro is perfect, just use that and check the space again in like 6 months to see if something’s beaten it. https://huggingface.co/hexgrad/Kokoro-82M
The model is good, but I will say their inference code leaves a lot to be desired. I had to rewrite large portions of it for simple things like correct chunking and streaming. The advertised expressive keywords are very much hit and miss, and the devs have gone dark unfortunately.
https://github.com/mlang/llm-tts
Strictly speaking, even music generation fits the usage pattern: text in, audio out.
llm-tts is far from complete, but it makes it relatively "easy" to try a few models in an uniform way.