A Next.js application that performs real-time speech transcription and translation using OpenAI's models. This app captures live audio input, provides real-time transcription, and simultaneously translates the content into your selected target language.
- 🎤 Live audio capture and transcription
- 🌍 Real-time translation to multiple languages
- 🔄 Automatic text cleanup option (keep last 3 sentences)
- 💻 Clean, modern user interface
- 🎯 Support for 10+ target languages
Before you begin, ensure you have the following installed:
- Node.js 16.8 or later
- npm or yarn package manager
- A modern web browser with microphone support
- An OpenAI API key (for production use)
- Clone the repository:
git clone <repository-url>
cd speech-transcription-app- Install dependencies:
npm install
# or
yarn install- Create a
.env.localfile in the root directory and add your OpenAI API key:
OPENAI_API_KEY=your_api_key_here- Start the development server:
npm run dev
# or
yarn dev- Open http://localhost:3000 in your browser.
- Select your target translation language from the dropdown menu.
- Click the "Start Recording" button to begin capturing audio.
- Speak clearly into your microphone.
- The app will display the original transcription on the left and the translation on the right.
- Toggle the "Keep only last 3 sentences" switch to manage text length.
- Click "Stop Recording" when finished.
- English (en)
- Spanish (es)
- French (fr)
- German (de)
- Italian (it)
- Portuguese (pt)
- Russian (ru)
- Japanese (ja)
- Korean (ko)
- Chinese (zh)
This application is built with:
- Next.js 13 (App Router)
- TypeScript
- Tailwind CSS
- OpenAI API
- Web Audio API
- React Icons
Contributions are welcome! Please feel free to submit a Pull Request.
This project is licensed under the MIT License - see the LICENSE file for details.
- OpenAI for providing the speech-to-text and translation APIs
- Next.js team for the excellent framework
- All contributors and users of this application