{"id":97027,"plugin_id":"plugin_asdk_app_6abd51b0891c81918954286cdd388fa3","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-11-15T06:36:30.203Z","digest":"22fe7e49dcdf2a2b1132a31074341a0c4521db21d87c3469498932338b7dd8b5","against":null,"payload":{"description":"Turn speech in an audio or video file into text. Use for transcripts, subtitles, meeting notes and interviews, with speaker labels when asked.","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":215}],"name":"audio-transcription","skill_md_contents":"---\nname: audio-transcription\ndescription: Turn speech in an audio or video file into text. Use for transcripts, subtitles, meeting notes and interviews, with speaker labels when asked.\n---\n# Transcribe audio\n\n1. Get the recording as an `https` link to an audio or video file.\n2. Choose a model: call `list_models` with `category` set to `transcription`, unless the user names one.\n3. Call `transcribe_audio` with the `model` and the link as `file_url`. Set `diarize` to true when the user wants each speaker labelled, and `smart_format` to true for punctuation, numbers and dates.\n4. A long recording returns a job id: call `get_job` with it, and again until the transcript is ready.\n5. Reply with the transcript. Offer a summary, action items or subtitles made from it.\n\nIf the user has a file and no link, ask for a link: the tool reads recordings from links.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}