Chapters
Overview
The Chapters Task divides video or audio content into time-coded segments with titles or summaries for each part.
It helps structure long-form content — such as podcasts, talks, or tutorials — into easily navigable chapters that can be displayed in players or apps.
When complete, the task creates a Track file with "kind": "chapters"
and a .json
or .vtt
file containing the chapter list.
Example Output
Creating a Chapters Task
You can create a Chapters task directly from a file or URL,
or include it as part of a workflow.
Webhook Example
When processing completes, the results will be sent to your webhook endpoint.
File Structure
Property | Type | Description |
---|---|---|
id | string | Unique file ID for the chapter track. |
object | string | Always "track". |
kind | string | Always "chapters". |
language | string | Detected or target language code (ISO 639-1). |
format | string | Output format ("json" or "vtt"). |
filename | string | Chapter file name. |
duration | number | Duration of the associated media file in seconds. |
filesize | number | Size of the output file in bytes. |
url | string | Public URL of the chapters file. |
chapters | array | List of chapter segments with index, start, end, and title. |
created / updated | string (ISO 8601) | Creation and update timestamps. |
Supported Inputs
Chapters tasks can be generated from:
-
Video files:
.mp4
,.mov
,.webm
-
Audio files:
.mp3
,.m4a
,.wav
Example Workflow Integration
Chapters are often created as part of an automation workflow,
alongside other track types such as subtitles and thumbnails.
This automation converts uploaded videos to MP4 and generates
subtitles, thumbnails, and chapters automatically.
Example Chapter File (VTT Format)
Common Use Cases
-
Creating chapter markers for podcasts and long-form videos
-
Adding timeline navigation in media players
-
Segmenting content for search or summarization
-
Auto-generating “table of contents” for educational videos
Summary
The Chapters task divides a video or audio file into structured, time-coded segments.
It’s ideal for long-form content and can be automatically triggered via workflows or webhooks.