A React Native application that uses OpenAI's Whisper API for audio transcription.
- Install dependencies:
npm install- Create a
.envfile in the root directory and add your OpenAI API key:
OPENAI_API_KEY=your_openai_api_key_here
- Start the development server:
npm start- Record audio using the device's microphone
- Transcribe audio using OpenAI's Whisper API
- Display transcription results in real-time
- Node.js
- npm or yarn
- Expo CLI
- OpenAI API key
- iOS or Android device (or emulator) for testing
- Press the "Start Recording" button to begin recording audio
- Press "Stop & Transcribe" when you're done recording
- Wait for the transcription to complete
- View the transcribed text on the screen
Make sure to replace the placeholder API key in the .env file with your actual OpenAI API key before running the application.