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.
Related
- 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.