mimic3 VS tortoise-tts

I'd like to take advantage of high quality TTS models but I'd prefer it to be one I may host myself.

Haven't found the right way yet, I'm considering: https://github.com/MycroftAI/mimic3

Fast or good, choose one

Mozilla's TTS is a python package installable with pip and uses cpu or gpu resources to render a choice of voices, they mostly sound natural and this is the good. https://github.com/mozilla/TTS

Mycroft's mimic3 is the default voice renderer for the Mycroft project that runs on pi hardware and sounds ok-ish, that is the fast. https://github.com/MycroftAI/mimic3

There are many others but these are the two I use according to if it needs to run on limited hardware or if the cycles fall freely from the sky.

It took quite a bit of digging to find the repo link https://github.com/MycroftAI/mimic3#readme and it's AGPL-3 for those interested in such things

Recently seeing this testing mailserver linked on HN: https://tweedegolf.nl/en/blog/86/introducing-mailcrab

I was reminded of another useful tool, mimic3 by MycroftAI that gives you very nice TTS: https://github.com/MycroftAI/mimic3

So I was wondering: what other useful apps have been containerized for easy setup and great usefulness?

Basically the point of this question is to let people share these, for the benefit of all.

You could also try the successor but they didn't get around implementing the harvard voice yet and we don't like any of the voices that come with it.

https://github.com/MycroftAI/mimic3 this? it can be easily hosted on docker as well

I use Tortoise TTS. It's slow, a little clunky, and sometimes the output gets downright weird. But it's the best quality-oriented TTS I've found that I can run locally.

https://github.com/neonbjb/tortoise-tts

neonbjb/tortoise-tts

EDIT: It appears to be the exact same issue as this

It was primarily being used to train TTS models (see https://github.com/neonbjb/tortoise-tts), which largely fit into a single GPUs memory. So, for data parallelism, x8 PCIe isn't that much of a concern.

Previously TortoiseTTS was associated with PlayHT in some way, although the exact connection is a bit vague [0].

From the descriptions here it sounds a lot like AudioLM / SPEAR TTS / some of Meta's recent multilingual TTS approaches, although those models are not open source, sounds like PlayHT's approach is in a similar spirit. The discussion of "mel tokens" is closer to what I would call the classic TTS pipeline in many ways... PlayHT has generally been kind of closed about what they used, would be interesting to know more.

I assume the key factor here is high quality, emotive audio with good data cleaning processes. Probably not even a lot of data, at least in the scale of "a lot" in speech, e.g. ASR (millions of hours) or TTS (hundreds to thousands). As opposed to some radically new architectural piece never before seen in the literature, there are lots of really nice tools for emotive and expressive TTS buried in recent years of publications.

Tacotron 2 is perfectly capable of this type of stuff as well, as shown by Dessa [1] a few years ago (this writeup is a nice intro to TTS concepts). With the limit largely being, at some point you haven't heard certain phonetic sounds before in a voice, and need to do something to get plausible outcomes for new voices.

[0] Discussion here https://github.com/neonbjb/tortoise-tts/issues/182#issuecomm...

[1] https://medium.com/dessa-news/realtalk-how-it-works-94c1afda...

Tortoise GitHub repo - Source code, documentation, and usage guide

TorToiSe (https://github.com/neonbjb/tortoise-tts) produces the best quality speech of any freely available model. However, its long inference times makes it impractical for voice chatbots like Gdansk.