Jump to content

Any easily trainable TTS system?


Recommended Posts


I am working on a small project and, in the near future, I'd like to implement some sort of Text-To-Speech system. The caveat is that it should be somewhat trainable.

Basically, I don't just need TTS but also that it can be trained with, say, my voice to have a similar tone. For example, if I read the test sentences mumbling (but still kind of resembling the actual sounds), the TTS would turn text into mumbles which kind of sound like the actual sounds. Is there anything like that out there already?

I found Merlin (https://github.com/CSTR-Edinburgh/merlin/) and Voice Cloning but they are kind of rough around the edges, especially when it comes to train them with my own data.

Anyone who has worked on similar systems?


Link to comment
Share on other sites

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.

Reply to this topic...

×   Pasted as rich text.   Paste as plain text instead

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.


  • Recently Browsing   0 members

    • No registered users viewing this page.
  • Create New...