Insert keyframes based on audio analysis

Insert keyframes based on audio analysis, for example:1) Dialogue (based on specific words, inserting an animation keyframe when the word "hello" is spoken).This way, we can zoom in on the image when the word "hello" is spoken.2) Select a piece of music, analyze it, and specify that keyframes should be placed on that bass drum or kick. The analysis is based on the selected region, as in iZotope RX 11.