Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/dustland/talk
IELTS Talk Master
https://github.com/dustland/talk
ielts nextjs15 openai tts whisper
Last synced: about 13 hours ago
JSON representation
IELTS Talk Master
- Host: GitHub
- URL: https://github.com/dustland/talk
- Owner: dustland
- License: mit
- Created: 2024-11-12T18:07:37.000Z (2 days ago)
- Default Branch: main
- Last Pushed: 2024-11-13T05:06:28.000Z (1 day ago)
- Last Synced: 2024-11-13T05:21:14.534Z (1 day ago)
- Topics: ielts, nextjs15, openai, tts, whisper
- Language: TypeScript
- Homepage: https://talk.dustland.ai
- Size: 237 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Talk Master
An AI-powered IELTS Speaking practice platform that provides real-time feedback, evaluation, and scoring.
[](https://opensource.org/licenses/MIT)
[](https://nextjs.org/)
[](https://openai.com/)
[](https://www.typescriptlang.org/)
[Online](https://talk.dustland.ai) · [Report Bug](https://github.com/dustland/talk/issues) · [Request Feature](https://github.com/dustland/talk/issues)
## ✨ Features
- 🎯 Real-time IELTS speaking practice for all three parts
- 🎙️ Voice recording with automatic transcription
- 🤖 AI-powered evaluation and scoring
- 💡 Detailed feedback on pronunciation, grammar, and vocabulary
- 🔊 Text-to-Speech for reference answers
- 📊 Band score calculation following official IELTS criteria
- 🎨 Modern and responsive UI with dark mode support
## 🚀 Getting Started
### Prerequisites
- Node.js 20+
- pnpm
- OpenAI API key
### Installation
1. Clone the repository
```bash
git clone https://github.com/dustland/talk.git
```
2. Install dependencies
```bash
pnpm install
```
3. Set up environment variables
```bash
cp .env.example .env.local
```
Add your OpenAI API key to `.env.local`:
```env
OPENAI_API_KEY=your_api_key_here
```
4. Run the development server
```bash
pnpm dev
```
Open [http://localhost:3000](http://localhost:3000) with your browser to see the result.
## 🛠️ Tech Stack
- [Next.js 15](https://nextjs.org/) - React framework
- [TypeScript](https://www.typescriptlang.org/) - Programming language
- [Tailwind CSS](https://tailwindcss.com/) - CSS framework
- [Shadcn/ui](https://ui.shadcn.com/) - UI components
- [OpenAI API](https://openai.com/api/) - AI models (GPT-4o, Whisper, TTS)
- [Framer Motion](https://www.framer.com/motion/) - Animations
## 📖 Usage
1. **Select Speaking Part**: Choose between Part 1 (Introduction), Part 2 (Long Turn), or Part 3 (Discussion)
2. **Start Recording**: Click the "Start Speaking" button to begin recording your answer
3. **Stop Recording**: Click "Stop Recording" when finished
4. **Review Feedback**:
- View your transcribed answer
- See detailed AI feedback
- Check your band scores
- Listen to a reference answer
## 🤝 Contributing
Contributions are welcome! Here's how you can help:
1. Fork the repository
2. Create your feature branch (`git checkout -b feature/AmazingFeature`)
3. Commit your changes (`git commit -m 'Add some AmazingFeature'`)
4. Push to the branch (`git push origin feature/AmazingFeature`)
5. Open a Pull Request
## 📝 License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
## 🙏 Acknowledgments
- [OpenAI](https://openai.com/) for providing the AI models
- [Vercel](https://vercel.com/) for hosting
- [Shadcn](https://twitter.com/shadcn) for the amazing UI components
- IELTS speaking test format and criteria
## 📧 Contact
Dustland - [@dustland_ai](https://x.com/dustland_ai) - [email protected]
Project Link: [https://github.com/dustland/talk](https://github.com/dustland/talk)
---
Made with ❤️ for IELTS learners and AI enthusiasts