Inspect a local media file — video, audio recording, or document — and report what it is: duration, resolution, page count, codec, available tracks (audio / subtitle / text layer), and whether transcription (ASR) and OCR are available for this file. (读取本地媒体的元信息：时长、分辨率、页数、编码、可用轨道（音轨 / 字幕轨 / 文本层）， 以及能否做 ASR / OCR 的初判。)

Call this FIRST on any file you have not inspected yet. It costs no image tokens and decodes nothing. Then pick the right next tool:

• video / audio -> media_overview to read it

• document -> media_overview to see page thumbnails and per-page text

• a specific moment or page -> media_zoom for a close-up

• "where was X said / on which page" -> media_locate for a timestamp or a page number

For audio it also reports a quick health check — average level, speech ratio and silence ratio — so you know whether the recording actually contains audible speech before you spend an ASR call on it. A recording that is effectively silent is reported as such and is never sent to ASR (no hallucinated transcript).

This server never downloads anything and never calls an LLM: you always pass a local absolute path, and it only prepares images and text for your own model to look at.

Build an overview of a local media file so you can read it without guessing. (生成媒体总览：视频出分镜宫格图与按时间对齐的文本清单；录音出带时间轴的转写；文档出页面缩略图与每页文字。)

What you get depends on the media:

• video : one or more numbered storyboard grids (each cell carries its cell number) plus a time-aligned text index of every cell

• audio : a timestamped transcript, segment by segment

• document : a grid of page thumbnails plus the text of each page, when a document parser is configured

TEXT SOURCE ORDER — subtitles first, ASR only as a fallback:

1. a transcriptFile you pass in (external subtitle file),

2. the subtitle track embedded in the container,

3. a subtitle file with the same base name in the same directory (a.srt next to a.mp4),

4. ASR — only when none of the above exists and an ASR provider is configured. Every segment is tagged with its source. subtitle = the author's own words, safe to quote. asr = machine transcription: names, numbers and jargon are often wrong, so do NOT quote an ASR segment verbatim and do not present it as the speaker's exact words. visual = there is no text at all, only the picture.

The storyboard grid is for FINDING things, not for reading them: cells are small, so text inside a cell is usually unreadable. To read text on screen, call media_zoom on that moment and read the cropped single frame.

The full text is NOT inlined. It is written to disk and the returned paths point at it: content.md (readable), segments.jsonl (one segment per line, machine-readable), manifest.json (what was produced and how). Read those files section by section and summarise them in chunks yourself — do not ask for the same range again just to get more inline text.

Always call media_probe first: it tells you how long the file is, whether a subtitle source exists, and which transcript source applies, for free. Long media must be narrowed with start/end (video, audio) or pages (document) — one giant grid of a two-hour film gives you illegible cells and spoils the ending. Follow the continuation hint in the result to page through the rest.

Get a close-up of one moment in a local video, or one page of a local document, returned as a single image. (取本地视频某一时刻的特写单帧，或本地文档某一页的整页 / 局部放大图。)

Use it after media_overview when one cell or page needs a closer look: "what exactly is on screen at 01:12?" "what does line 3 of page 7 say?"

For video, pass at (a single timestamp) or start/end (a window — the sharpest frame inside it is returned, and the exact timestamp is reported back). For a document, pass page, optionally with crop. crop is {x, y, width, height}, each a fraction 0..1 of the frame or page, origin top-left.

Keep it to one frame. It costs roughly 1,900 vision tokens — far more than a whole overview cell. Zoom the parts that matter instead of re-scanning the file.

This is the ONLY tool whose image is meant for reading. A storyboard cell is a few hundred pixels wide and the text inside it is unreadable; a cropped single frame at up to 1600 px is readable. So: locate in the overview grid, then zoom to read. The returned image is always source "visual" — what you read off it is your own reading of pixels, not a transcript, so treat it as an observation rather than a quotation.

Find where something appears in a local media file and return its position: a timestamp (milliseconds and seconds) for a video or recording, a page number for a document. (定位：给一段文本或关键词，返回它在视频 / 录音里的时间戳，在文档里的页码。)

Use it when you know roughly what was said but not when ("where does it mention X"), or when you need to know which page a phrase is on. Matching ignores punctuation, spacing and case, and works for both Chinese and English. Long phrases match better than single characters.

Text only by default — no image, no pixels spent. Add includeFrame: true to also get the picture at the best match (one image, roughly 1,900 vision tokens).

A transcript is required: the embedded subtitle track, a transcriptFile you pass in, or ASR configured via MMGREP_ASR_PROVIDER. Subtitles win over ASR. If none is available this tool says so instead of guessing. Use media_overview if you only need the visuals.

Each match is tagged with its source. A match whose source is "asr" came from machine transcription, so the wording may be wrong (names, numbers, jargon) — do not present it as the speaker's exact words.

Read subtitles for a local media file and return them as timestamped segments. (读取本地字幕文件或视频内嵌字幕轨，解析成带时间轴的段落列表。)

Two sources, in this order: an explicit transcriptFile (a local .srt, .vtt, .ass or .ssa file), or the subtitle track embedded in the container. Auto-discovery also picks up a sibling file with the same base name in the same directory (a.srt next to a.mp4) when neither of the above is available — the source and the exact path are always reported back, never silently.

No image and no pixels spent: the result is text with millisecond and second timestamps. Use media_locate to search inside the subtitles. Use media_overview if you also want to see what is on screen.