Convert voice commands to file actions

Converting voice commands to file actions involves integrating speech recognition, natural language processing (NLP), and file system automation. This setup can be useful for hands-free operations like opening, renaming, deleting, or organizing files via spoken commands.

Technologies Required

• Speech Recognition: To transcribe spoken commands (e.g., SpeechRecognition or Google Speech-to-Text).

• Natural Language Processing: To understand the intent (e.g., spaCy, transformers, or simple pattern matching).

• File System Control: To perform actions (e.g., Python’s os, shutil, or pathlib).

Sample Workflow in Python

python
CopyEdit
import os
import speech_recognition as sr

def recognize_speech():
    recognizer = sr.Recognizer()
    with sr.Microphone() as source:
        print("Listening for command...")
        audio = recognizer.listen(source)
        try:
            command = recognizer.recognize_google(audio)
            print("You said:", command)
            return command.lower()
        except sr.UnknownValueError:
            print("Sorry, could not understand.")
        except sr.RequestError:
            print("Could not request results.")
    return None

def execute_file_action(command):
    if "create file" in command:
        filename = command.split("create file")[-1].strip()
        with open(filename, 'w') as f:
            f.write("")
        print(f"File '{filename}' created.")

    elif "delete file" in command:
        filename = command.split("delete file")[-1].strip()
        if os.path.exists(filename):
            os.remove(filename)
            print(f"File '{filename}' deleted.")
        else:
            print(f"File '{filename}' not found.")

    elif "rename file" in command:
        parts = command.split(" to ")
        if len(parts) == 2 and "rename file" in parts[0]:
            old_name = parts[0].replace("rename file", "").strip()
            new_name = parts[1].strip()
            if os.path.exists(old_name):
                os.rename(old_name, new_name)
                print(f"File renamed from '{old_name}' to '{new_name}'.")
            else:
                print(f"File '{old_name}' not found.")

    elif "open file" in command:
        filename = command.split("open file")[-1].strip()
        if os.path.exists(filename):
            os.system(f"start {filename}")  # use 'open' for macOS, 'xdg-open' for Linux
            print(f"Opening file '{filename}'...")
        else:
            print(f"File '{filename}' not found.")

    else:
        print("Command not recognized or unsupported.")

if __name__ == "__main__":
    while True:
        spoken_command = recognize_speech()
        if spoken_command:
            if "exit" in spoken_command or "quit" in spoken_command:
                print("Exiting.")
                break
            execute_file_action(spoken_command)

Supported Voice Commands Examples

• “Create file notes.txt”

• “Delete file old_data.csv”

• “Rename file report.doc to summary.doc”

• “Open file project_plan.pdf”

Enhancements

• Add confirmation prompts before destructive actions.

• Use language models to parse more complex commands.

• Incorporate a GUI or voice feedback for accessibility.

• Extend to directory actions or cloud storage.

Would you like this integrated into a desktop application or used via terminal/CLI?