Back to Projects
PythonAudio AI20
Real-Time Voice & Emotion Processing
Real-time speech-to-text with Whisper and emotion recognition from audio, streamed over Flask and WebSocket with live microphone capture.
whispernlpflaskwebsocketemotion-recognition
Key Highlights
Real-time Whisper ASR with WebSocket streaming
Multi-class emotion recognition (happy, sad, angry, neutral, fearful)
Live audio capture from microphone via PyAudio
Combined transcript + emotion timeline output
Flask backend with WebSocket support
Tech Stack
PythonOpenAI WhisperFlaskWebSocketlibrosaPyAudioNumPy
GitHub Repository
github.com/ErdoganPeker/Real-Time-Voice-and-Emotion-Processing