Use the Speak AI MCP server tool export_media to export a media file’s transcript,
insights or labels in various formats (pdf, docx, srt, vtt, txt, csv).
What does it do?
Export a media file’s transcript, insights or labels in various formats (pdf, docx, srt, vtt, txt, csv). Use fileType csv-labels for a labels CSV with one row per labelled passage and label (file name, group, label, times, speaker, excerpt, author, status, confidence, comment count). Generates the file and returns it without saving or sharing anything.
Parameters
export_media takes 8 parameters, 2 of them required.
| Name | Type | Required | Description |
|---|---|---|---|
mediaId |
string | Yes | Unique identifier of the media file |
fileType |
enum | Yes | Desired export format |
isSpeakerNames |
boolean | No | Include speaker names in export |
isSpeakerEmail |
boolean | No | Include speaker emails in export |
isTimeStamps |
boolean | No | Include timestamps in export |
isInsightVisualized |
boolean | No | Include insight visualizations |
isRedacted |
boolean | No | Apply PII redaction to export |
redactedCategories |
array of string | No | Specific categories to redact |
Behaviour
The Speak AI MCP server publishes these behaviour hints for export_media.
- Only reads data. Does not modify your workspace.
- Does not delete or overwrite existing data.
- Repeating an identical call can have an extra effect.
- Stays inside Speak AI. Does not reach other systems.
Related
- Exports lists the rest of the Exports category.
- Tool reference lists every Speak AI MCP server tool.
- MCP server covers setup, supported clients, and what agents can do once connected.