stt microphone live example

[ChitranshS]

• [x] I understand that this repository is auto-generated and my pull request may not be merged

Changes being requested

This PR adds a real-time speech-to-text example script demonstrating how to use OpenAI's WebSocket-based transcription API. The script:

1. Captures audio from the microphone in real-time
2. Streams the audio data to OpenAI's transcription API via WebSockets
3. Processes and displays transcription events as they occur
4. Handles speech detection events (speech start/stop)
5. Properly manages resources and connections

This example would be valuable for users who want to implement real-time transcription functionality in their applications using the OpenAI API.

Additional context & links

This implementation uses:

• websockets for WebSocket communication
• sounddevice for microphone input
• numpy for audio data processing
• pydantic for data validation and configuration

The script demonstrates best practices for real-time audio streaming and event handling with OpenAI's transcription API, including proper connection management, error handling, and resource cleanup.