Declare the source of the data for the Summarization job.
📝 Note that some sources have different parameter requirements.

• generic - Generic-format .txt and JSON transcripts
• audio - For uploaded audio files
• wordcab_transcript - Summarization job with one Wordcab transcript using a transcript_id
• signed_url - AWS, GCP or Azure presigned URL
• vtt - A VTT file or string
• rev_ai - Use the JSON array from Rev.ai's monologues object as input
• assembly_ai - Use the JSON array from AssemblyAI's utterances object as input
• deepgram - Use the JSON array from Deepgram's utterances object as input
• vtt - Either a .vtt file, or raw VTT text in the request body - Learn more about proper vtt formatting.
  Note that speaker labels are required for a VTT source.
• otter - Learn more about Otter.ai transcript formatting
• fireflies - Learn more about Fireflies.ai transcript formatting
• sonix - Learn more about Sonix.ai transcript formatting
• descript - Learn more about Descript transcript formatting
• teams- Use a .docx transcript from the Microsoft Teams application.

A human-readable name for your job. Not strictly required, but highly recommended.

Default value: narrative
The type of summary you want to generate.

• narrative - Wordcab's default summary type, a chronological play-by-play that aims to extract all relevant details. Best for customer support calls.
• conversational - A summary that suits internal meetings and sales calls when you don't need an exact play-by-play of the events. Consider choosing narrative if you do.
• no_speaker - Similar to the conversational summary, without referencing any speakers and going straight to the important events in a conversation.
• brief - A summary type that provides a title and a single-sentence summary for each section of transcript. It's ideally used by pairing with Context Items to get a detailed overview of the transcript.

Context features provide additional context to Wordcab summaries, focusing on the most important aspects of the transcript.

• issue - This item represents the main problem or concern that the section of transcripts aims to address.
• purpose - This item describes the primary goal or objective of the transcript.
• keywords - This item is an array of important words or phrases relevant to the document's content.
• next_steps - This item is the recommended next action conveyed by one or more speakers.
• discussion_points - This item is an array of notable topics discussed in the document.

A comma-separated string of numbers 1 through 5. 1 corresponds to the shortest summary length, and 5 to the longest.
📝 Note that if you specify more than one number, you will receive multiple summaries.

Required when source is set to wordcab_transcript.
Represents the id of a processed Wordcab transcript.

Required when source is set to signed_url.
An AWS, GCP or Azure presigned URL that points to an audio file.

A comma-separated string containing tags you'd like to attribute to your job. This is particularly helpful when you want to see summarized minutes and request counts for a particular subset of customers.

Default value: en
Set the language of the input source.
You can find a detailed overview of supported languages here.

Default value: en
Set the language for the resulting summary.
You can find a detailed overview of supported languages here.

Default value: transcribe,summarize
A comma-separated list of actions to take upon initiating the job. Generally, there is no need to change this, unless you use transcribe on its own - this will generate a Wordcab transcript, and you can use the resulting transcript_id for further downstream tasks.

A metadata object is composed of a key-value pair. To add metadata to your job, you must add X-Wordcab-Metadata-<Key> headers to your /summarize request, where <Key> is a key of your choice.
This way a metadata object with the key-value pairs you initially set will be saved to your job object. By convention, Wordcab will extract anything after X-Wordcab-Metadata- (in this case, <Key>), make the string lowercase, and then convert any dashes to underscores.
For example, an X-Wordcab-Metadata-UUID key with a value of "abc", and an X-Wordcab-Metadata-User-ID key with a value of "123" will result in the following metadata object when retrieving your job: "metadata": { "uuid": "abc", "user_id": "123" }