How to chapterize my transcription?

How to chapterize my transcript?

The Chapterization model segments audio into distinct chapters with descriptive headlines and summaries. This makes it easier to navigate and extract insights from long audio recordings such as meetings, lectures, or podcasts.

This feature is in Alpha state.

Overview

Automatically segments audio into logical chapters.
Each chapter contains:
- Start and end times
- Summary
- Headline
- Bottom-line gist
- Keywords

This enables users to quickly scan and understand the structure of long audio content.

Usage

Enable chapterization in your transcription request by setting the chapterization flag to true.

Request Example


{
	"audio_url": "<your audio URL>",
	"chapterization": true
}

Response

When enabled, the transcription result includes a chapterization key with structured chapter data.


{
	"transcription": { ... },
	"chapterization": {
		"success": true,
		"is_empty": false,
		"results": [
			{
				"summary": "In a world where minimalism is valued, yet excess is desired, hope for the future remains. The past predicts the present, which is yet to be determined.",
				"headline": "Headline: \\\\"Embracing Hope: The Interconnectedness of Past, Present, and Future\\\\"",
				"gist": "Embracing Hope: Past, Present, Future Interconnected",
				"keywords": [
					"Split infinity",
					"less is more",
					"too much",
					"hope",
					"present"
				],
				"start": 0.0,
				"end": 19.83977
			}
		],
		"exec_time": 5.078396797180176,
		"error": null
	}
}

Response Fields

Field	Type	Description
`success`	boolean	Indicates if the chapterization was successful.
`is_empty`	boolean	Returns `true` if no chapters were detected.
`results`	array	List of detected chapters with metadata.
`summary`	string	A descriptive summary of the chapter’s content.
`headline`	string	A concise headline capturing the chapter’s theme.
`gist`	string	The bottom-line takeaway of the chapter.
`keywords`	string[]	Key terms extracted from the chapter.
`start`	float	Chapter start time (in seconds).
`end`	float	Chapter end time (in seconds).
`exec_time`	float	Execution time of the model (in seconds).
`error`	string	Error message if chapterization fails, otherwise `null`.