Asynchronous Transcription

Asynchronous transcription is a good starting point for generating meeting transcripts if you know you don't need this data in real-time time.


To run asynchronous transcription on a bot's recording, you can use the Analyze Bot Media endpoint once a bot has reached the done state.

In addition to transcription, this endpoint can be used to run AI analysis on recordings such as summarization.

When an analysis job is done, you'll receive an analysis_done webhook event, at which point you can:


Job failures

If an analysis job fails, you will receive an analysis_failed bot status change event.

Upon receiving this event, can use the Retrieve Job endpoint to fetch details about why the job failed.


What are the parameters in the Analyze Bot Media endpoint?

These parameters are exactly the parameters that the transcription provider accepts, and are passed through verbatim to the transcription provider.

For example the assemblyai_async_transcription.language_code controls the AssemblyAI parameter documented here:

For detailed information on each parameter, we recommend viewing the corresponding transcription provider's own API documentation.