AssemblyAI

Export your transcript in SRT or VTT format for subtitles and closed captions

Advanced options: Characters per Caption

Output	Type
Subtitles	JSON

Apply Large Language Models to spoken data using the AssemblyAI LeMUR framework

Advanced options: Endpoint, Final Model, Max Output Size, Questions, Temperature, Transcript IDs

Output	Type
LeMUR Response	JSON

Retrieve a list of transcripts from AssemblyAI with filtering options

Input	Type	Required
Assembly API Key	str	Yes
Limit	int	No

Advanced options: Created On, Status Filter, Throttled Only

Output	Type
Transcript List	JSON

Poll for the status of a transcription job using AssemblyAI

Input	Type	Required
Transcript ID	other	Yes
Assembly API Key	str	Yes

Advanced options: Polling Interval

Output	Type
Transcription Result	JSON

Create a transcription job for an audio file using AssemblyAI with advanced options

Advanced options: Audio File URL, Format Text, Language, Automatic Language Detection, Punctuate, Expected Number of Speakers, Speech Model

Output	Type
Transcript ID	JSON