问题
How to feed the audio stream output of the AWS Kinesis video stream (KVS) to AWS Transcribe service and get realtime audio to text conversion? I ingested audio via amazon connect to KVS(Kinesis video stream), My concern is, which format kinesis video stream (KVS) deliver (I hope its Payload format) and will Transcribe service able to support it or any way I can convert to Transcribe service understandable.
回答1:
For me, I tinkered with the AWS CLI, two stage process although the output from the get-data-endpoint is sent directly for a single command line execution:
export ARN=arn:aws:kinesisvideo:XXX
aws kinesis-video-media get-media --stream-arn ${ARN} --start-selector StartSelectorType=EARLIEST outfile --endpoint-url `aws kinesisvideo get-data-endpoint --stream-arn ${ARN} --api-name GET_MEDIA --output text`
that got me the file I could then deal with as I needed... obviously, all my AWS credentials and so on were configured.
HTH - Robert...
来源：https://stackoverflow.com/questions/55204098/how-to-feed-the-audio-stream-output-of-the-aws-kinesis-video-stream-to-aws-trans