# PopUp Archive & Audiosear.ch {% embed url="" %} ## Notes * Make audio searchable! * PopUp Archive came first, and now Audiosear.ch People come to them with content, so that is what POpUp Archive is used for. Download files, get SRT (if WebVTT), and if public, back up at Internet Archive. Audiosear.ch is a full text podcast search API, importing and transcribing tons of podcasts all the time and making it available via API and extracting entities, keywords, topic clustering * Topic clustering via machine learning -- put them in "unsupervised training buckets" Cultural analysis -- what do people on the internet think about this? * Thinking about features as "Will this bring more people to the podcast table?" * Searching within the text to find exactly where a keyword is mentioned * Experimental Twitter videos – clips from podcasts with transcripts (because Twitter mutes video by default) * Categorize podcasts by language type / topics (e.g. colloquial, politics, NSFW, relationships) and plot on scatter charts * API: --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://textav.gitbook.io/textav-event/services/popup-archive-and-audiosearch.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.