Can the automation of transcriptions be done ? So what i am asking is can Uipath software be used to download audio and return a typed document ?
I don’t believe there is any direct integration or activities pack for speech to text, however, it wouldn’t take much for you to set up a workflow that integrates with AWS Transcribe for example. This takes audio files you have stored in an S3 bucket and outputs a JSON file which you can access via an API. Its pretty advanced and can identify different speakers for you.
You could then use UiPath to both upload the audio file to AWS, kick off the reading of that to text, then access the output via the API. RPA tools are a friendly way of achieving this kind of integrated solution to a business problem, with next to no coding required.