Project Description

I would like to be able to give my fingers a well deserved rest from time to time, so I'd love to be able to either control my computer with voice or simply dictate to it, for writing emails and so on, and if possible... even writing some code using my voice!

Goal for this Hackweek

(This is for hackweek 2022!)

  • Research the state of DeepSpeech
  • make nerd dictation work with my window manager
  • try out mycroft-core for computer control
  • Write a frontend for ease of configuration
  • Write a nice blog post about it

Resources

It's almost sad that while doing some research, voice over/text to speech solutions on other platforms (linux) are almost non existent, and those that exist are either discontinued or abandoned... however I found:

The following projects seem to still be active:

https://github.com/ideasman42/nerd-dictation https://github.com/alphacep/vosk-api/

Then there's mozilla's text to speech https://github.com/mozilla/DeepSpeech

and then there's mycroft (which can be use for voice control) https://github.com/MycroftAI/mycroft-core

More: https://youtu.be/71qERo6fLqo?t=789

PS: Looking into talon and eye tracking software such as ~OptiKey~ [windows only] is also a valid option here (also this is wild, https://twitter.com/devdevcharlie/status/1444861827427356676?s=20 and works!)

Looking for hackers with the skills:

Nothing? Add some keywords!

This project is part of:

Hack Week 21

Activity

  • over 2 years ago: dsterba liked this project.
  • over 2 years ago: dvenkatachala liked this project.
  • over 2 years ago: fos liked this project.
  • over 2 years ago: punkioudi liked this project.
  • over 2 years ago: alarrosa liked this project.
  • over 2 years ago: HarrisonWAffel liked this project.
  • almost 3 years ago: hennevogel liked this project.
  • almost 3 years ago: szarate started this project.
  • almost 3 years ago: szarate originated this project.

  • Comments

    • szarate
      over 2 years ago by szarate | Reply

      • Deepspeech requires python 3.6 https://deepspeech.readthedocs.io/en/r0.9/?badge=latest

    • szarate
      over 2 years ago by szarate | Reply

      Looks like I'll end up with a frankenstein, but https://github.com/omlins/JustSayIt.jl also looks promising,

    Similar Projects

    This project is one of its kind!