Transcribing audio files
The V‑Cloud API consists of two core methods:
POSTrequests containing an audio file or a zip file less than 250MiB containing one or more audio files to transcribe. Successful
/transcriberequests return a
requestidto identify results for retrieval and tracking.
GETrequests containing a valid
/transcribe/resultrequests return a URL with the results as a zip or JSON file. The format of your results depends on the options specified in the initial
V-Cloud limits the
/transcribeendpoint to 128 concurrent connections per IP address and the
/transcribe/resultendpoint to 32 concurrent connections per IP address.
The following sections provide reference information for and examples of using each of these methods, plus an example of setting up a simple callback server and using it with the
Passing transcription parameters
V‑Cloud transcription parameters, often referred to as stream tags, enable you to customize how each audio file will transcribe. Transcription parameters are key-value pairs passed in the body of the request. The syntax of a parameter is
, as shown in the following example:
curl -F email@example.com \
-F token=your-token-here \
-F emotion=true \
Refer to V‑Cloud transcription parameters for more information.