Welcome to the Urdu Voice Chatbot project! This repository showcases a Streamlit application that allows users to interact with a chatbot using Urdu voice input and receive responses in Urdu.
The Urdu Voice Chatbot is designed to:
- Record Urdu Voice Input: Users can record their voice in Urdu using the integrated audio recorder.
- Convert Voice to Text: The recorded voice is transcribed into Urdu text using Google's Speech Recognition API.
- Generate AI Responses: The transcribed text is processed by Gemini’s Generative AI model to generate a relevant response.
- Convert Text to Voice: The generated response is then converted back into Urdu speech using Google's Text-to-Speech (TTS) API.
- Interactive Interface: The Streamlit interface provides a user-friendly way to interact with the chatbot.
- Streamlit: For creating the interactive web interface.
- Google Speech Recognition API: For converting spoken Urdu into text.
- Gemini Generative AI: For generating intelligent responses in Urdu.
- Google Text-to-Speech API: For converting text responses back into speech.
-
Clone the Repository
git clone https://github.com/your-username/urdu-voice-chatbot-streamlit.git cd urdu-voice-chatbot-streamlit
-
Create a Virtual Environment
python -m venv venv source venv/bin/activate # On Windows, use `venv\Scripts\activate`
-
Install Dependencies
pip install -r requirements.txt
-
Set Up Secrets Create a
.streamlit/secrets.toml
file and add your API keys:[gemini] api_key = "YOUR_API_KEY_HERE"
-
Run the App
streamlit run voicechatbot.py
This application is also deployed on Streamlit Cloud. You can access the live app here: Your Streamlit App URL
Contributions are welcome! Please open an issue or submit a pull request if you have suggestions or improvements.
For any inquiries or feedback, please reach out to me at E-mail.
I am Ahmad Ali Rafique, an AI & Machine Learning specialist with a focus on building intelligent applications. My expertise includes deep learning, natural language processing, and creating interactive applications using modern technologies. You can find more about my work on GitHub and connect with me on LinkedIn.