Tasks
Transcribe Task
This task transcribes an audio file to text. Provided with a Stubber fileuuid, this task will transcribe the file and make the resulting
text available in the data. This can be used for eg. voice notes in Whatsapp, or the voice note field in Stubber.
The rest of this document assumes familiarity with adding a task to a stub. See tasks documentation
Basic usage
Parameters
files
whisper models, as
can be seen here. It can also be seen that the
file size limit is 25MB. Default: null
model
whisper model versions are allowed at the moment. Only the
whisper-1 model is supported at the moment. The latest information can be found here Default: whisper-1
disable_model_response
_update_from_transcribe_task feedback action. This can be disabled by setting this parameter
to true. Default: false
Result
Properties
request
fileuuid, filename and contentType are as expected. response
text property. If multiple files are supplied,
the response will be an array with an object containing a text property for each file supplied. Examples
Single voice note and disable model response
The task definition:
Result
Using multiple files
You can also pass multiple files to the transcribe task. With the Stubber voicenote field, you can record multiple voice notes in a single field, or you can add multiple voice notes fields, and pass the first file of each field as an item in the files array. The latter approach is applied here.
The task definition: