Wordcab's API takes a conversation - whether in the form of an audio file, a .vtt file, or a JSON object, among other supported formats - and returns a summary and additional valuable insights.
To make the summary process as simple and intuitive as possible, Wordcab's API is split into several logical components. The API accepts one of several Sources to summarize. Each summary process is called a Job, consisting of Transcript and Summary objects. More details are below:
- Jobs: Jobs are created whenever you initiate a new process - whether this is transcription, summarization, or anything else. Each job has a
job_namethat you can use to poll for status (see the Job Status guide) and retrieve other useful data.
- Sources: We accept a variety of input sources. For more on the types of
sourceswe accept. Please see the Accepted Sources guide.
- Transcripts: Wordcab's API accepts audio or text as input and transforms it into a structured Transcript, which can be used (and re-used) for downstream tasks such as summarization and topic extraction.
- Summaries: Wordcab's bread-and-butter. Summaries are highly-condensed versions of transcripts, often reducing read times by over 90%.
- Summary Types: Wordcab is capable of generating a variety of customizable summary types, including
no_speakersummaries. Check out Summary Types for more details.
The following guides will introduce the Wordcab API's mechanics and walk you through many practical use cases.
Updated 7 months ago
⏩ Let's talk about Authentication.