Use the Speak AI MCP server tool create_clip to create a highlight clip from one
or more media files by specifying time ranges.
What does it do?
Create a highlight clip from one or more media files by specifying time ranges.
Clips are processed asynchronously (states: queued, processing, completed, failed).
Use get_clips to check status. Maximum total clip duration is 30 minutes. Use
multiple timeRanges to stitch segments from different media files together. When the
clip finishes processing it fires your clip_created automations, whose steps can
send email, post to Slack, call webhook URLs or run connected third-party app
actions.
Parameters
create_clip takes 6 parameters, 3 of them required.
| Name | Type | Required | Description |
|---|---|---|---|
title |
string | Yes | Title for the clip |
mediaType |
enum | Yes | Output media type |
timeRanges |
array of object | Yes | Array of time ranges to include in the clip. Each specifies a source media and start/end times. |
description |
string | No | Description of the clip |
tags |
array of string | No | Tags for the clip |
mergeStrategy |
enum: CONCATENATE | No | How to merge multiple segments (default: CONCATENATE) |
Behaviour
The Speak AI MCP server publishes these behaviour hints for create_clip.
- Can change data in your workspace.
- Can delete or overwrite data. Use with care.
- Repeating an identical call can have an extra effect.
- Can reach systems outside Speak AI.
Related
- Clips lists the rest of the Clips category.
- Tool reference lists every Speak AI MCP server tool.
- MCP server covers setup, supported clients, and what agents can do once connected.