{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Phony.ai","title":"Why Sub-Second Voice AI Is an Architecture Problem, Not a Speed Problem","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/fefafd68\"></iframe>","width":"100%","height":180,"duration":307,"description":"Voice AI latency figures are everywhere — but without a shared measurement definition, they're nearly impossible to compare. This episode breaks down the four-leg pipeline that every caller silently waits through, and explains why shaving milliseconds off the model is often the wrong place to look.","thumbnail_url":"https://img.transistorcdn.com/DCzXpShZdzXzDVoqJ6cLSbwoXfpZHNldXkJek6FNhAo/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS80ZGFm/OWI2NGE4NTZhNDM2/OTE4MjhkOTJhY2Uy/OTZjNC5wbmc.webp","thumbnail_width":300,"thumbnail_height":300}