• Jacek Jarmulak

Voicegain releases RTC Callback API for telephony IVRs and bots

Updated: Sep 13

If you always wanted to build you own telephony based Voice Bot or a speech-enabled IVR but did not know where to start then we have something for you - Release 1.12.0 of Voicegain Speech-to-Text Platform now includes RTC Callback API together with easy phone provisioning from our portal.

With this, a web backend developer can design, code, and launch a brand new telephony based voice bot or speech IVR in a day. You can code the application logic in a programming language of your choice - Java, Python, Node.js - as long as it is able to serialize data into the JSON format. Developers can also code and deploy the application logic in a serverless computing environment like Amazon Lambda.

Many enterprises - in banking, financial services , health care, telecom and retail - are stuck with legacy telephony based IVRs that are approaching obsolescence.

Voicegain's RTC Callback APIs provide a great future-proof upgrade path for such enterprises. Since these APIs are based on web callbacks, they can interact with any backend programming language. So any backend web developer can design, build and maintain such apps.

What is RTC Callback API ?

RTC stands for Real Time Communications - currently it means phone calls, but we will very soon release WebRTC support.

Callback API is a Web API where the actual program/implementation is on the Client side and the Voicegain Callback APIs define the Requests and Responses. The meaning of Requests and Responses is reversed w.r.t what you would see in a normal Web API:

  • Responses provide the commands, while

  • Requests provide the outcome of those commands.

Illustrated example of RTC Callback API in action

Below is an example of a simple phone call interaction which is controlled by RTC Callback API. The sequence diagram shows 4 callbacks during a toy survey call:

  • Req 1: Phone Call arrived

  • Resp 1: Say: "Welcome"

  • Req 2: Done saying "Welcome"

  • Resp 2: Ask: "Are you happy", bind reply to happy var

  • Req 3: Caller's answer was "yes", happy=YES

  • Resp 3: Disconnect

  • Req 4: Disconnected

  • Resp 4: We are done

Currently supported actions

RTC Callback API supports 4 types of actions:

  • output: say something - TTS with a choice of 8 different voices is supported

  • input: ask question - both speech input and DTMF are supported. For speech input you can use GRXML, JSGF or built-in grammars

  • transfer: transfer a call to a phone destination

  • disconnect: end the call

Wait, there is more

Each call can be recorded (two channel recording) and then transcribed. The recording and the transcript can be accessed from the portal as well as via the API.


Features coming soon:

  • record Callback action - you can use it to implement voicemail or record other types of messages

  • transfer to a sip destination

  • input - allow choice of large vocabulary speech-to-text in addition to grammars - use the captured text in your NLU

  • answer call at a sip address - instead of a phone number

  • WebRTC support

  • outbound dialing

Further Reading

Contact Us