I want to develop a system with asterisk where I have agents who speak English. Now, I want that if someone calls agents and they speak a different language other than English then I want that language to be converted to English because the agent only speaks English and also when the agent speaks English we have to convert his voice to that language which the caller speaks. Is it possible?
Let’s Say, The Caller is French, now when he speaks we have to convert his voice to English so the agent can understand what he/she is saying and also when the agent speaks English we have to convert that to French so the caller can understand what the agent is talking.
This is serious engineering work. The individual components should be available as open source software, but a functioning overall package would still require a lot of work. Aside from that, I would still be concerned about performance and unacceptable time delays.
I would also see legal problems with such an approach. In a professional environment, a certain quality of translation must also be required. Who should pay if the translation leads to costly errors?
Then What should I do now? Can it be done by recording both parties and using Google speech to text ? maybe using a dialplan and asterisk-java library? . Let’s say I use AGI for speech-to-text but I do not know How will the dialplan go to the next step when it will still be during the call and how will we separate both parties’ recordings? I have been trying to find a solution for the last 10 days but could not. It would be great If you give me some example of this.
I don’t know anything about a magical asterisk-java library. The different media streams are already separated, but you also need to keep the original streams. That’s basically a conference and one could easily switch, in case. Let me whisper words of wisdom: let it be.
All of the components are present to be able to do so. It’s up to you to put the pieces together. ARI has the ability to snoop on a channel for example[1] which can be used to passively fork audio. Once done ARI also provides external media[2] functionality to direct media outside of Asterisk to an application. What happens there is up to you. There is an example of an external media implementation on Github[3]. If you’re wanting a complete out of the box solution though, then that doesn’t exist from the project. We’re a toolkit, it’s up to you to use what we provide to do what you need in many cases.