- Newest
- Most votes
- Most comments
If you are thinking of using translate then the input has to be in text since translate only accepts text as input.
So you can make use of Transcribe ---> translate ---> Polly
Tanscribe converts the speech into text and then you can change it to english using translate and then use polly (text to speech)
https://docs.aws.amazon.com/transcribe/latest/dg/streaming.html
https://docs.aws.amazon.com/polly/latest/dg/what-is.html
Please make sure that you are using the realtime API calls for the above services.
Please refer to this link as it may help you!
Regarding the chat channel, there are some scenarios already implemented by other customers that are solving this approach. They leverage Amazon translate with Amazon Connect to allow this cross language interaction between agents and customers. Have a look to this blog post for more info.
For the voice channel, there are no out of the box integrations that allow to implement this approach as easy as with the chat channel.
If you are still interested in having this approach with the voice channel you will have to implement a custom solution. This solution will have to leverage the Amazon Translate and Amazon Transcribe services (for translate audio transcriptions), Amazon kinesis Video Streams (For streaming the audio of the call into those services) and finally Amazon Polly (for passing from the translated text to speech).
There are no public resources to share on this approach, so if you are still interested on it and need more guidance I suggest you to contact your specific AWS team (Account manager or solution architect).
Relevant content
- Accepted Answerasked 2 years ago
- AWS OFFICIALUpdated a year ago
- AWS OFFICIALUpdated a year ago
- AWS OFFICIALUpdated 10 months ago
- AWS OFFICIALUpdated 3 years ago
So I want to know whether the input will be inform of audio right?