Transcription functions like real time recognition except results are saved to a text file at the end of the call.
To activate transcription, you have to use the record method with the transcribe parameter set to true and the language parameter set to one of the supported languages. Here is how it should look like:
To retrieve the transcription results, you need to call the GetCallHistory HTTP API method; the response will contain the records field with transcription URL(s) with a 3-month lifetime. By default, each line in the transcription file is prefixed "Left" for an audio stream from a call endpoint to the Voximplant cloud, and "Right" for an audio stream from the Voximplant cloud to a call endpoint. Once a transcription is completed, the TranscriptionCompleteCallback is executed.