get_transcript

Read the recording narration behind a document or a single input.

Returns what the person said while recording — the narration the document’s tickets were generated from. Pass a documentId for every transcribed input on that document, or an inputId for a single recording.

This is supporting context. The tickets from get_document remain the spec; use the transcript to understand intent or resolve a vague reference, not to invent extra work.

Input

documentId · string (uuid)

Id of the Montra document whose input transcripts to read.

inputId · string (uuid)

Id of a single input (recording) whose transcript to read. Ticket inputId values from get_document work here.

Output

transcripts · object[] · required

One entry per transcribed input.

Show properties

inputId · string · required

Id of the input this transcript belongs to.

title · string · required

Title of the input.

kind · string · required

What kind of input it is, such as a recording.

text · string · required

The narration as spoken. For older captures whose plain text was never stored, this is rebuilt from the segments with a [mm:ss] timestamp on each line.

segments · object[] · required

Timed segments of the narration. Empty when the transcript has none.

Show properties

text · string · required

What was said in this segment.

startMs · number · required

Segment start, in milliseconds. null when the transcript did not record one.

endMs · number · required

Segment end, in milliseconds. null when the transcript did not record one.

transcriptRevisionId · string · required

Id of the exact transcript version returned.

createdAt · string · required

When that transcript version was created.

truncated · boolean · required

true when this transcript’s text or segments were cut short by the response caps.

truncated · boolean · required

true when any returned transcript was cut short.

Notes

• Pass exactly one of documentId or inputId. Passing both, or neither, is rejected.
• Inputs without a transcript are dropped from the result: text inputs never have one, and a recording is transcribed in the background, so a recent one may still be processing. When nothing on the document has a transcript yet, the call comes back with a message saying so — retry later rather than concluding there was no narration.
• The response is capped across all transcripts at 200,000 characters and 2,000 segments so a long recording cannot flood your context. Whatever is cut is flagged by truncated, both per transcript and at the top level.
• An input that has not been filed into a document yet is still being classified and reads as not found, as does anything hanging off a document outside the bound workspace. See workspace binding.