TensorFlowTTS

Hey HN, has anyone found a viable solution for doing this locally and offline on iOS? I'd like to offer a privacy-friendly text to speech feature to my App, and Apple's speech synthesis sounds awful compared to some newer models and TTS engines. The only thing I've found is an older TensorFlowTTS example here: https://github.com/TensorSpeech/TensorFlowTTS/tree/master/examples/ios Any pointers or tips appreciated.

The problem is mostly about model training and architecture. I was doing TTS like 2.5/3 years ago and most models were train on fixed (+/- 5-10s) clips with like avg of 80 words or so, there were few attempts for fixing that and if I remember correctly few RNN-based models were good at ignoring input length and generate "good" audio but new flow-based and diffusion based models are out of my domain as I'm in CV for past few years and only read some new cool paper once in a while :) You can also search for postags (and token ids for them) that are especially placed for "pause" audio as they often fix problem with weird transition when you split the sentences. This repo -> https://github.com/TensorSpeech/TensorFlowTTS was very good few years back.

I had a lot of success using FastSpeech2 + MB MelGAN via TensorFlowTTS: https://github.com/TensorSpeech/TensorFlowTTS. There are demos for iOS and Android which will allow you to run pretty convincing, modern TTS models with only a few hundred milliseconds of processing latency.

For open source offline TTS with more or less recent algorithms you can check https://github.com/TensorSpeech/TensorFlowTTS

Recent more or less reasonable one is https://github.com/TensorSpeech/TensorFlowTTS, it implements all the latest algorithms. For simple business books it will be ok, for emotional fiction probably not there yet.