TTS VS tortoise-tts

lol this marketing technique is getting very old. https://github.com/coqui-ai/TTS is already amazing and open source.

Not sure how relevant this is but note that Coqui TTS (the realistic TTS) has already shut down

https://coqui.ai

I've used coqui.ai's TTS models[0] and library[1] to great success. I was able to get cloned voice to be rendered in about 80% of the audio clip length, and I believe you can also stream the response. Do note the model license for XTTS, it is one they wrote themselves that has some restrictions.

[0] https://huggingface.co/coqui/XTTS-v2

[1] https://github.com/coqui-ai/TTS

My only exposure to Coqui was their text to speech software. If I remember correctly the website was a commercialized service with TTS and probably some other related things. I hope the software work continues in the open.

https://github.com/coqui-ai/TTS

Coqui.ai TTS (https://github.com/coqui-ai/TTS)

"tts_models/multilingual/multi-dataset/xtts_v2" model from https://github.com/coqui-ai/TTS. It gives pretty good results and works with references, so it's pretty easy to change the voice. By the way the source code of the project is open: https://github.com/volotat/Anagnorisis but be ready, the code is pretty raw for now.

A recent update to their GitHub also has a no-code gradio ui to facilitate fine-tuning and inferencing locally. https://github.com/coqui-ai/TTS/releases/tag/v0.21.3

No API token found for 🐸Coqui Studio voices - https://coqui.ai

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.