Amazon is the host of AWS Re: INVENT today, its developer conference for everything related to AWS. And the company has just announced a promising new service called Amazon Transcribe. The service is now available as a preview and goes beyond many automated transcription services.
Now that the video and the audio have surpbaded the web, it has become more difficult to badyze the information within those media formats. One way to do this is to transcribe the audio part and convert it into text. The text is indexable, you can search and open new possibilities.
With Amazon Transcribe, the company has created a speech recognition engine. It allows you to convert an audio file stored in your Amazon S3 account in grammatically correct text.
Amazon Transcribe works in English and Spanish at the moment. But the company promised that many more languages will be added in the coming weeks.
The secret sauce behind Amazon Transcribe is that the service can intelligently format and add score. The service can also recognize multiple speakers and add timestamps so you can isolate each part of a conversation.
Amazon mentioned several use cases. For example, Transcribe can help you create automatic subtitles for online videos. It is also a good way to record customer service calls and badyze them.
The service works with low bit-rate audio files, such as call recordings, and you can add your own vocabulary if you want to help the service understand the names of the products.
Amazon Transcribe will also be useful with Amazon Translate and Amazon Comprehend, two new services announced today. In this way, you can convert audio recordings into meaningful data.