Talon-AI-Tools

Control large language models and AI tools through voice commands using the Talon Voice dictation engine.

This functionality is especially helpful for users who:

• want to quickly edit text and fix dictation errors
• code by voice using tools like Cursorless
• have health issues affecting their hands and want to reduce keyboard use
• want to speed up their workflow and use AI commands across the entire desktop

Prompts and extends the following tools:

• Github Copilot
• OpenAI API (with any GPT model) for text generation and processing
  • Any OpenAI compatible model endpoint can be used (Azure, local llamafiles, etc)
• OpenAI API for image generation and vision

Help and Setup:

1. Download or git clone this repo into your Talon user directory.

2. Obtain an OpenAI API key.

3. Create a Python file anywhere in your Talon user directory.

4. Set the key environment variable within the Python file

Caution

Make sure you do not push the key to a public repo!

# Example of setting the environment variable
import os

os.environ["OPENAI_API_KEY"] = "YOUR-KEY-HERE"

5. See the GPT or Copilot folders for usage examples.

Note

You can use this repo without an OpenAI key by customizing the endpoint url to be your preferred model.

You can also exclusively use this repo with just Copilot if you do not need LLM integration

Quickstart Video