Use the Speak AI MCP server tool update_transcript_speakers to update or rename
speaker labels in a single media transcript.
What does it do?
Update or rename speaker labels in a single media transcript. Call get_transcript
first to read the speaker list: a speaker’s label is whatever it was last renamed
to, not a fixed value, so ids from an earlier turn may be stale. Renaming a speaker
to a name another speaker already has is refused as a collision. Re-sending a rename
that has already been applied is a safe no-op, so do not retry a call that reported
success.
Parameters
update_transcript_speakers takes 2 parameters, all of them required.
| Name | Type | Required | Description |
|---|---|---|---|
mediaId |
string | Yes | Unique identifier of the media file |
speakers |
array of object | Yes | Speakers to rename. Each entry maps one existing speaker to its new name; speakers not listed are left untouched. |
Behaviour
The Speak AI MCP server publishes these behaviour hints for
update_transcript_speakers.
- Can change data in your workspace.
- Can delete or overwrite data. Use with care.
- 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.