Skill UI

Use Azure OpenAI Realtime Mini to turn text prompts into streamed PCM audio, convert it to WAV, and deliver base64 payloads for frontend playback, handling transcripts and voice tuning for podcast-style narration.

This skill guides the development of advanced voice agents, representing the frontier of natural human-AI interaction. It covers both low-latency Speech-to-Speech (S2S) architectures (like OpenAI Realtime API) and fully controllable STT→LLM→TTS pipelines. Key focus areas include minimizing end-to-end latency (targeting <800ms), handling conversational nuances, background noise, and managing interruptions for applications like customer support, IVR, and live translation.

Reference for building real-time voice and multimodal AI applications with Daily and Pipecat transports, covering pipelines, STT, TTS, LLM integration, tool calling, context management, and turn detection.

Expert in building voice AI applications - from real-time voice agents to voice-enabled apps. Covers OpenAI Realtime API, Vapi, Deepgram, ElevenLabs, LiveKit, and WebRTC. Focuses on low-latency, production-ready voice experiences.