This skill enables developers to integrate real-time text-to-speech and audio narrative generation into their applications using the Azure OpenAI Realtime API. It provides standardized workflows for connecting via WebSockets, handling streaming PCM audio chunks, converting data to WAV format, and managing transcript synchronization. Ideal for creating interactive podcasts, voice-guided narratives, or accessibility tools that require low-latency, natural-sounding synthetic speech with specific voice personas like Alloy, Echo, or Shimmer.
주요 기능
01Support for multiple distinct voice personas including Alloy, Nova, and Onyx
02Pre-configured Azure OpenAI Realtime API integration patterns
03Low-latency real-time audio streaming via WebSockets
04Automated PCM to WAV format conversion logic
05Synchronized transcript generation alongside audio delivery
0640,583 GitHub stars
사용 사례
01Building automated podcast generation pipelines from written articles or blog posts
02Creating interactive AI narrators for immersive storytelling applications
03Developing accessibility tools that provide real-time audio versions of dynamic text content