Yes, you have the option to delete files yourself. If and when you delete files all copies and any derivative material, transcripts, etc. are immediately and irretrievably deleted.
Yes, we have our own proprietary speech engine.
We use parallel processing and split the audio file into 1 minute chunks. Thus, we chop a 5 minute call into 5 one min pieces and send them out to multiple servers for processing. For example, if the job is a 5 min video, we can send back to you within 90 secs-3 mins. We also provide SLAs and 99% guarantee for 10 min, 2 hr, 24 turn around.
VoiceBase uses Amazon Simple Storage Service (Amazon S3), which is storage for the Internet. You can use Amazon S3 to store and retrieve any amount of data at any time, from anywhere on the web. You can accomplish these tasks using the simple and intuitive web interface of the AWS Management Console. With Amazon S3, you can request that your API responses - the JSON documents containing the transcript, keywords, topics, phrase spotting, and prediction results - be automatically exported to one of your Amazon S3 buckets. This is an add-on feature that happens in addition to any callbacks you also configure. S3 is a popular and easy to use storage system, and is supported by nearly every ETL, BI, and Big Data vendor as a native data source. In the first version, VoiceBase will provide developers with a pre-tested script that can be used along with callbacks to provide S3 export. In a later version, S3 export will be integrated with the Developer Portal UI and made even more automated.