Skip to content

Get Transcript

Retrieve the full transcript for a media file with speaker labels and timestamps.

Updated View as MarkdownAsk ClaudeOpen in ChatGPTllms.txt

Use the Speak AI MCP server tool get_transcript to retrieve the full transcript for a media file with speaker labels and timestamps.

What does it do?

Retrieve the full transcript for a media file with speaker labels and timestamps. Works on processed media and also returns the partial, in-progress transcript while a meeting bot is still recording (LIVE_TRANSCRIPT state). To fetch only the new sentences added since your previous call during a live meeting, use get_live_meeting_transcript instead. Use update_transcript_speakers to rename speaker labels after reviewing. For subtitle-formatted output, use get_captions instead.

Parameters

get_transcript takes 1 parameter, all of them required.

Name Type Required Description
mediaId string Yes Unique identifier of the media file

Behaviour

The Speak AI MCP server publishes these behaviour hints for get_transcript.

  • Only reads data. Does not modify your workspace.
  • Does not delete or overwrite existing data.
  • Repeating an identical call is safe.
  • Stays inside Speak AI. Does not reach other systems.
  • Media library lists the rest of the Media library category.
  • Tool reference lists every Speak AI MCP server tool.
  • MCP server covers setup, supported clients, and what agents can do once connected.
Navigation

Type to search…

↑↓ navigate↵ selectEsc close