Ending timestamp (in milliseconds) of the portion of audio being summarized.
An ultra-short summary, just a few words, of the content spoken during this timeframe.
A single sentence summary of the content spoken during this timeframe.
Starting timestamp (in milliseconds) of the portion of audio being summarized.
An ultra-short summary, just a few words, of the content spoken during this timeframe.
Generated using TypeDoc
Auto Chapters provides a "summary over time" for audio files transcribed with AssemblyAI. It works by first segmenting your audio files into logical "chapters" as the topic of conversation changes, and then provides an automatically generated summary for each "chapter" of content.
For more information on Auto Chapters, check out the announcement on our blog.
When submitting a file for transcription, simply include the
auto_chaptersparameter in yourPOSTrequest, and set this totrue.When your transcription is completed, you'll see a
chapterskey in the JSON response, as shown on the right. For each chapter that was detected, the API will include thestartandendtimestamps (in milliseconds), asummary- which is a few sentence summary of the content spoken during that timeframe, a shortheadline, which can be thought of as a "summary of the summary", and agist, which is an ultra-short, few word summary of the chapter of content.