Cognitive Speech-to-Text Recognition Motivation [VCS 21.4 UG]

The Speech-to-Text service enables you to perform automatic speech to text detection on your video content. Analyze your video files using the VidiNet media service and automatically populate them with transcription metadata.

If you are looking at doing automatic subtitling of you assets, this tool is the perfect fit to get you started.

Seamless integration into any VidiCore Server, anywhere. 

Requirements:

• Video files must be under VidiCore Server management on a storage with S3 storage method.

• Requires VidiCore version 5.0 or later.

• Content must be in a region where Amazon Transcribe is available. See regions where Amazon Transcribe is available here.

Supported formats:

mp4 (maximum 4 hours or 2 GB)

Supported languages:

See supported languages in the Amazon Transcribe documentation.