- Newest
- Most votes
- Most comments
Currently Transcribe supports 1 or 2 channel audios, which can be processed together or separately. Please see these link. https://docs.aws.amazon.com/transcribe/latest/dg/how-input.html#how-input-channels https://docs.aws.amazon.com/transcribe/latest/dg/channel-id.html
If you need to process more than 2 audio channel, there may be ways to create multiple Transcribe instances to handle that. Are you able to detail your application, source formats and current workflow?
- Phone call related workflow? Recorded audio file? Video+audio processing?
- audio files only? audio channels from a video?
Thanks for the response. Our application is involved with court reporting. We capture audio files from several different microphones during a session, and upload them for transcription later. So there's no video or real-time processing.
We discussed solving the problem with multiple Transcribe jobs. It will require a lot of work on our end since we already have a system built for 1 or 2-channel processing, but if that's the best way to do it we'll proceed. I wanted to check first to see if there was some easier way. I'd hate to do 100 hours of work if Amazon is planning to increase this limit soon.
Frank
Relevant content
- asked 5 years ago
- asked 3 years ago
- asked 2 months ago
- asked 4 years ago
- AWS OFFICIALUpdated a year ago
- AWS OFFICIALUpdated 2 years ago
- AWS OFFICIALUpdated 9 days ago
- AWS OFFICIALUpdated a year ago