{ "opencollection": "1.0.0", "info": { "name": "Google Books About Audio Understanding API", "version": "1.0.0" }, "items": [ { "info": { "name": "Audio Understanding", "type": "folder" }, "items": [ { "info": { "name": "Google Upload File (Resumable)", "type": "http" }, "http": { "method": "POST", "url": "https://www.googleapis.com/books/v1/files", "headers": [ { "name": "X-Goog-Upload-Protocol", "value": "" }, { "name": "X-Goog-Upload-Command", "value": "" }, { "name": "X-Goog-Upload-Header-Content-Length", "value": "" }, { "name": "X-Goog-Upload-Header-Content-Type", "value": "" }, { "name": "X-Goog-Upload-Offset", "value": "" }, { "name": "Content-Length", "value": "" } ], "body": { "type": "json", "data": "{}" } }, "docs": "Upload a video, PDF, audio, or other media file using resumable upload protocol. Use this for files larger than 20MB, \nvideos longer than approximately 1 minute, or when you want to reuse the file across multiple requests.\n" }, { "info": { "name": "Google Count Tokens", "type": "http" }, "http": { "method": "POST", "url": "https://www.googleapis.com/books/v1/models/:model:countTokens", "params": [ { "name": "model", "value": "", "type": "path", "description": "The model to use for token counting" } ], "body": { "type": "json", "data": "{}" } }, "docs": "Get a count of the number of tokens in content, including audio, video, images, and text.\nUseful for estimating costs and ensuring content fits within model context windows.\n" }, { "info": { "name": "Google Generate Content", "type": "http" }, "http": { "method": "POST", "url": "https://www.googleapis.com/books/v1/models/:model:generateContent", "params": [ { "name": "model", "value": "", "type": "path", "description": "The model to use for generation" } ], "body": { "type": "json", "data": "{}" } }, "docs": "Generates text output from various inputs including text, images, video, audio, and PDF documents.\n\n**Document Understanding**: Process PDF documents up to 1000 pages using native vision to:\n- Analyze and interpret text, images, diagrams, charts, and tables\n- Extract information into structured output formats\n- Summarize and answer questions based on visual and textual elements\n- Transcribe document content (e.g., to HTML) preserving layouts and formatting\n- Process multiple PDFs in a single req" } ] } ], "bundled": true }