Update Readme.md
Browse files
README.md
CHANGED
|
@@ -11,3 +11,64 @@ license: mpl-2.0
|
|
| 11 |
---
|
| 12 |
|
| 13 |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
# Voice AI - Chat & Voice Assistant 🎙️🤖
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
## 🌟 Overview
|
| 21 |
+
Voice AI is an interactive chatbot that supports both **text and voice-based conversations**. Built using **Streamlit, Whisper API, LLaMA 3, and Edge TTS**, it provides a seamless experience where users can **speak or type their queries** and get **AI-generated responses** in both **text and speech formats**.
|
| 22 |
+
|
| 23 |
+
## 🚀 Features
|
| 24 |
+
- 🎤 **Voice Input**: Record your voice and get AI-generated answers.
|
| 25 |
+
- 📝 **Text Input**: Type questions and receive intelligent responses.
|
| 26 |
+
- 🔊 **Text-to-Speech (TTS)**: AI responses are converted to speech and played back.
|
| 27 |
+
- 📜 **Conversational Memory**: Holds the conversation history in the session.
|
| 28 |
+
- 🎶 **Dynamic Audio File Naming**: Each response generates a new numbered audio file.
|
| 29 |
+
- 🌍 **Hosted on Hugging Face Spaces**: Accessible anywhere, anytime.
|
| 30 |
+
|
| 31 |
+
## 🏗️ Technologies Used
|
| 32 |
+
- **Streamlit**: UI Framework for interactive web apps.
|
| 33 |
+
- **Whisper API (Groq)**: Converts voice input to text.
|
| 34 |
+
- **LLaMA 3 (Groq)**: AI model for intelligent responses.
|
| 35 |
+
- **Edge TTS**: Converts AI-generated responses into speech.
|
| 36 |
+
|
| 37 |
+
## 📖 How It Works
|
| 38 |
+
1. **Start Chatting**
|
| 39 |
+
- Type your question OR press the **mic button** to record your voice.
|
| 40 |
+
2. **AI Processing**
|
| 41 |
+
- If using voice, your speech is converted to text.
|
| 42 |
+
- AI generates a relevant response based on the input.
|
| 43 |
+
3. **Response Output**
|
| 44 |
+
- The response is displayed on the screen.
|
| 45 |
+
- A voice response is also generated and played automatically.
|
| 46 |
+
4. **Continue the Conversation**
|
| 47 |
+
- Each new message is appended to the conversation history.
|
| 48 |
+
- Previous responses remain visible, and only the latest audio autoplays.
|
| 49 |
+
|
| 50 |
+
## 📦 Installation & Running Locally
|
| 51 |
+
If you want to run the project on your own machine:
|
| 52 |
+
|
| 53 |
+
### Prerequisites
|
| 54 |
+
- Python 3.8+
|
| 55 |
+
- Install dependencies
|
| 56 |
+
|
| 57 |
+
```bash
|
| 58 |
+
pip install -r requirements.txt
|
| 59 |
+
```
|
| 60 |
+
|
| 61 |
+
### Run the App
|
| 62 |
+
```bash
|
| 63 |
+
streamlit run app.py
|
| 64 |
+
```
|
| 65 |
+
|
| 66 |
+
## 🎭 Demo
|
| 67 |
+
Check out the live app on [Hugging Face Spaces](https://huggingface.co/spaces/your-space-name)!
|
| 68 |
+
|
| 69 |
+
## 📝 License
|
| 70 |
+
This project is licensed under the **MPL-2.0 License**.
|
| 71 |
+
|
| 72 |
+
---
|
| 73 |
+
💡 *Contributions & Feedback are Welcome!* 🚀
|
| 74 |
+
|