Giter VIP home page Giter VIP logo

Comments (4)

C-Nedelcu avatar C-Nedelcu commented on August 22, 2024 5

There is an issue with how most TTS APIs work and a reason why I can only get this to work properly under Chrome at the moment. In Chrome, you can basically push sentences to the TTS API stack, and the API will manage on its own. You can push several sentences at once, even while the current sentence is being spoken. The added sentences just pile up and are spoken one after the other.

From my trials with other APIs, they behave like this:

  • can't push another sentence while the current one is being spoken (the API just rejects it)
  • if you push two sentences consecutively, they will be spoken at the same time (so it sounds like garbage)

What's more, the scope of this addon is quite limited, it's basically an API experiment. It's in no way a long term professional product. I am happy to let anyone pick up the project and turn it into something greater, but I clearly lack the time and involvement to take this extension to the heights some users would want. The main issue being that with every update and iteration of ChatGPT, we come closer to an end. They will inevitably change the UI completely and the whole extension will become moot. And eventually, they will hopefully add proper TTS / STT functionality so that an extension like mine isn't needed.

These are the reasons why I am not currently considering adding external voices to the project. This project was basically to connect ChatGPT to the Chrome APIs (TTS/STT) and not much more. That being said I will gladly accept contributions to the projects, or forks, if anyone is willing to go down that road.

from talk-to-chatgpt.

Akis-M avatar Akis-M commented on August 22, 2024 3

This is exactly what I came here to say. We need more realistic voices to make the experience more immersive. The technology is already there. ElevenLabs etc... It's sad for such a great extension to hear voices from 1990 tech

from talk-to-chatgpt.

C-Nedelcu avatar C-Nedelcu commented on August 22, 2024

Hello there,

I have added ElevenLabs API support in v2.6.0.

This version has not been submitted to the Chrome/edge stores yet, I think it would need some beta testing first.
Would anyone please give it a try?

You have to install the new version manually, instructions are given on the project's home page.

I hope you enjoy it. I had fun testing it, the ElevenLabs voices are pretty great - even the default ones with a Free account.

from talk-to-chatgpt.

C-Nedelcu avatar C-Nedelcu commented on August 22, 2024

this has been live for a few days and seems to be working pretty great, so I'm going to close the issue :)

from talk-to-chatgpt.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.