Python Integration with Gemini AI

by

Here in this article we can see how we can Integrate Gemini AI In our python code.

  • We need to install speech recognition library
  • Now we need to recognize voice from the user, after recognize we can convert voice into the text, and then we can pass this text to Gemini AI.
  • For connectivity with gemini we required API secret key.
  • we can find it in Gemini official Developer Documentation
  • You need to create account and generate the API key, For API key you need to select the project,
    • You can create project in Google Cloud like Firebase.
  • Once you select the project it will generate the API key.

Source Code –

# PYTHON FOR VOICE

# 1. GET VOICE COMMAND FROM USER

#AIzaSyBakQATervFkxwe8e4YIz8E2KCU1yzvDb4

import speech_recognition as sr

import google.generativeai as genai

import os

from gtts import gTTS

import pyttsx3

recognizer = sr.Recognizer()

API_KEY=”AIzaSyBakQATervFkxwe8e4YIz8E2KCU1yzvDb4″

genai.configure(api_key=API_KEY)

def capture_voice_input():

    with sr.Microphone() as source:

        print(“Listening…”)

        audio = recognizer.listen(source)

    return audio

def convert_voice_to_text(audio):

    try:

        text = recognizer.recognize_google(audio)

        print(“You said: ” + text)

    except sr.UnknownValueError:

        text = “”

        print(“Sorry, I didn’t understand that.”)

    except sr.RequestError as e:

        text = “”

        print(“Error; {0}”.format(e))

    return text

def process_voice_command(text):    

    if “stop” in text.lower():

        return False

    else:

        model = genai.GenerativeModel(“gemini-1.5-flash”)

        response = model.generate_content(text)

        print(response.text)

        #tts = gTTS(text=response.text, lang=’en’)        

        #tts.save(“output.mp3”)

        engine = pyttsx3.init()

        engine.say(response.text)

        engine.runAndWait()

def main():

    end_program = False

    while not end_program:

        audio = capture_voice_input()

        text = convert_voice_to_text(audio)

        end_program = process_voice_command(text)

if __name__ == “__main__”:

    main()

Please feel free to add any comment if any doubt.

Thank You.

Share with our team

Leave a Comment