Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[new feature]Support for Command-Based Speech Input #496

Open
eecopilot opened this issue Mar 12, 2024 · 2 comments
Open

[new feature]Support for Command-Based Speech Input #496

eecopilot opened this issue Mar 12, 2024 · 2 comments
Labels
enhancement New feature or request

Comments

@eecopilot
Copy link

Description:
Currently, the speech-to-text plugin supports continuous speech input, transcribing everything the user says into text. However, it would be beneficial to have an additional mode that recognizes and returns only the most recent command spoken by the user, rather than transcribing the entire speech input.

This command-based speech input mode would be useful in scenarios where the user needs to issue voice commands to control an application or perform specific actions. Instead of returning a continuous stream of transcribed text, the plugin would intelligently detect and extract the most recent command uttered by the user, making it easier to integrate with command-based interfaces or voice-controlled applications.

Proposed Implementation:

  1. Add a configuration option or a separate mode to enable command-based speech input.
  2. Implement a command detection algorithm that can identify and extract the most recent command from the user's speech input.
  3. Provide a way to define or train the plugin to recognize specific commands or command patterns.
  4. Return only the most recent command detected, instead of the entire transcribed text.

Benefits:

  • Improved integration with command-based interfaces and voice-controlled applications.
  • Reduced overhead and clutter by returning only the relevant command, rather than continuous transcribed text.
  • Enhanced user experience by allowing more natural and efficient voice control.

Please consider implementing this feature as it would greatly improve the usability and versatility of the speech-to-text plugin.

@eecopilot
Copy link
Author

User can define several commands, and when the commands are heard, perform your own business logic in the callback.

@sowens-csd sowens-csd added the enhancement New feature or request label Mar 13, 2024
@sowens-csd
Copy link
Contributor

I've considered doing this as either a separate plugin or some new classes that work with Speech to text. It's a good idea as it fits in well with the intended goal of the plugin. I haven't had time to cleanup the classes that I use to do this for inclusion but I'll increase the priority of that if people would be interested. Please upvote this feature if anyone else is interested.

Thanks for the input!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

2 participants