Giter VIP home page Giter VIP logo

Comments (7)

Manamama avatar Manamama commented on August 22, 2024

Thank you: both versions 1.2 and 1.3 work great on the newest Chrome in Ubuntu.

Some tips about what to include in the Readme for the "GitHub newbies":

  • Add the link to the booklet marker that you had in the previous version 1.2. Even better: create the booklet code automatically here, with a clear direct link.
  • Tell them or direct them in the Readme to the Raw JS file. (Not everybody knows how GitHub UI works and what to click if they see it the first time.)
  • As per the request above, add "No output" to the Settings. It is fun and useful to listen in many cases, but gets annoying after a minute or two.

Otherwise a great tool which works in a couple of languages, subject to Google's STT and TTS capabilities, of course.

from talk-to-chatgpt.

Manamama avatar Manamama commented on August 22, 2024

Update: I have fed the code to ChatGPT and asked it to update with these missing features ;)
Modify this code so that there is a settings option for no voice output. Show me the change:

The results are more than promising:
_To add a settings option for no voice output, you can add a new variable called CN_NO_VOICE_OUTPUT and set it to false by default. Then, you can modify the CN_SayOutLoud function to check if CN_NO_VOICE_OUTPUT is true before speaking the text. If it is true, the function can simply return without calling the speechSynthesis.speak function.

Here is an example of how you can make this change:_
[...]
// Determine which word will cause this script to temporarily pause
var CN_SAY_THIS_WORD_TO_PAUSE = "pause";

// Set this to true to disable voice output
var CN_NO_VOICE_OUTPUT = true;

and then:

// This function will say the given text out loud using the browser's speech synthesis API
function CN_SayOutLoud(text) {
if (!text) return;

	// Check if no voice output is enabled
	if (CN_NO_VOICE_OUTPUT) return;

It also even created a Settings menu item after some gentle prompting ;), but something is messed up and it does not toggle:

// Open settings menu
function CN_OnSettingsIconClick() {
[...]

// 7. No voice output
var checkbox = document.createElement("input");
checkbox.type = "checkbox";
checkbox.id = "TTGPTNoVoiceOutput";
checkbox.checked = CN_NO_VOICE_OUTPUT;

checkbox.addEventListener("change", function(event) {
  CN_NO_VOICE_OUTPUT = event.target.checked;
});

I am tempted to fork it ...

from talk-to-chatgpt.

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

Haha that is brilliant. I will follow your suggestions. We need an account for ChatGPT so that it can propose changes itself

from talk-to-chatgpt.

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

In V1.4 I am planning:

  • settings persistence
  • skip button to stop reading current message
  • toggle button for text-to-speech (keeps bot quiet)

from talk-to-chatgpt.

Manamama avatar Manamama commented on August 22, 2024

Way to go, Nedelcu! Ta for listening to us.
For the time being, I had created two buttons, one with your talking 1.3 ver. code, the current one, and the second with my (ok, ChatGPT's: me being no coder) 1.3.1 default silence one.

A further feature request: add wget or like so that it can be fed by voice with live URLs ;)... (FYI, I manually tested this by pasting such content manually, and only 20 sentences or like are really fed into AI ChatGPT' episodic memory alas, despite GPT's self declarations that it can remeber all).

from talk-to-chatgpt.

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

Hello @Manamama
Can you tell me more about what you mean for your future request regarding wget? I am not sure I understand what you are trying to achieve? Do you want to feed a message that will be sent to the bot ? While that could be useful, it doesn't really fall into the scope of this project which is just to talk to the bot with voice.
Now, there could definitely be a toolbox project to add features to ChatGPT with your ideas and many more.

from talk-to-chatgpt.

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

Hello,

I have just published v1.4

  • settings are now saved in cookie and restored automatically
  • revamped menu
  • voice recognition toggle
  • text-to-speech toggle
  • skip current message button
  • menu border color changes based on current state (grey=idle, green=speaking, red=listening)
  • instead of an alert message, the browser will say 'OK' to indicate that it is ready

I think this means we can close the current issue.
Feel free to create a new thread if you have more features to suggest :)
I will be working on a Chrome extension soon

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.