transcript_read
Read bounded, incremental original transcript text for an audio or video task, using sequence offsets and optional time ranges to retrieve only new or relevant text.
Instructions
Read bounded incremental original text for an audio or video task. No images. trackId is the UUID returned by transcript_start; omitted selects the latest eligible same-source track. When subtitles and ASR coexist, explicitly read each desired trackId; no automatic merging or preference. after is last event sequence (initial0); pass nextAfter on subsequent calls so waits do not reread old events. Higher revision for a stable segment ID replaces prior text. limit1..500, default100. Optional source-second [start,end) filter; waitSeconds0..20 waits only for text. Returns source, original/mapped timestamps, final/provisional, requested/processed coverage and text status. acquisition separately reports decodedThrough, queueDepth, spooledBytes/maxSpoolBytes and its status; acquisition=complete does NOT mean transcription is complete. audioTransfer records streaming/retry/download-fallback status and provenance; use it to report whether a full audio download occurred. complete+speechStatus=no_speech differs from not_enabled/running/error. Untimed text stays unaligned.
The HOST chooses evidence depth from the user request and actual subtitle/ASR quality and coverage: text alone, selected storyboards, all storyboards, or targeted higher-quality follow-up. Subtitles, ASR and images are independently optional; choose any combination. For text-only media use audio_start/audio_url_start (audio-bearing video files/pages are accepted) without a visual job. No mandatory image retrieval, all-images rule, fixed answer format or mandatory ASR. Use video_review action=plan to record visual=none|selected|all; revise as evidence changes. Missing subtitles do NOT block usable images, and a video-only stream does not prove missing source audio. Each image response has a pending batch. Return images AND timestamp metadata to the model, inspect the chosen images, then call video_review action=ack with batchId and explicit viewedIndices (empty [] releases uninspected images without credit). ONLY THEN fetch another batch. Never accumulate many video_read calls inside one code/exec result: return control to the model after each bounded batch. Transport errors leave the batch pending: video_review replay retries it; status/reviewId support resume. Acknowledgement is a caller assertion, not proof of comprehension. Keep any semantic working notes in the Agent workspace, not in MCP evidence. Before finishing, video_review finish checks only the HOST-CHOSEN visual scope and pending image receipts, not text reading completion. The host must still judge if that scope answers the user, and state relevant gaps. Honest incomplete-work disclaimers do not justify abandoning feasible work. session_stop cleanup cancels processing but does not complete reading; user_cancelled is only for an explicit user cancellation. Audio-only workflows remain independent.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"id": "<id>"
},
"name": "transcript_read"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| end | No | ||
| after | No | ||
| limit | No | ||
| start | No | ||
| trackId | No | ||
| waitSeconds | No |