How to work with it?

[Ahtisham-1214]

I am creating a Text-to-speech project in Python where user will give English text as input and in response will get a voice accordingly. I want to use any Coqui TTS model, I just want to make it work. The documentation is a little confusing so please help me out.

[Ahtisham-1214]

It is also not working with Python 12 version

[eginhard]

First of all you should use our fork, which works with recent Python versions and has many other bug fixes: https://coqui-tts.readthedocs.io/en/latest/faq.html The original package hasn't been updated in 2 years.

Then see this page for how to use it: https://coqui-tts.readthedocs.io/en/latest/inference.html

[Ahtisham-1214]

First of all you should use our fork, which works with recent Python versions and has many other bug fixes: https://coqui-tts.readthedocs.io/en/latest/faq.html The original package hasn't been updated in 2 years.

Then see this page for how to use it: https://coqui-tts.readthedocs.io/en/latest/inference.html

but I want to use it in my project.
Since it has not been updated from 2 years, how would I use it in my project?

[eginhard]

As I said, you should use our fork, which is being maintained and gives you access to the same models and features as the original package. See these links for how to install and use it.

[Ahtisham-1214]

How can I simply fine-tune it for my project without cloning?

[eginhard]

See either

• https://coqui-tts.readthedocs.io/en/latest/models/xtts.html#training for XTTS
• or https://coqui-tts.readthedocs.io/en/latest/training/finetuning.html for all other models