Capture voice for Biometrics Authentication in IVR

Platform API
1

Hello,

I am working on integrating voice biometrics authentication. The goal is to capture 5 seconds of the caller's voice, save it as a WAV file, and send it to an external API for authentication.

The goal is for this to be transparent for the customer: he arrives in the IVR, starts chatting with the agent or voicebot and the IVR captures 5s of customer registration.

However, the /api/v2/conversations/{conversationID}/recordingmetadata API only authorizes the creation of a recording URL once the interaction has ended.

Is there any way to generate a downloadable audio file or AWS link of an audio segment belonging to an ongoing interaction?

Thanks for your help,

Sincerely,

2

Hello,

No, it is not possible at this time.
The available integration point to capture audio stream of an ongoing interaction is the AudioHook monitor integration.
This requires developing an "AudioHook server", following the protocol described on the Dev Center: AudioHook - Introduction.
A couple of pages on AudioHook are currently having a display issue. The dev engagement team is working on it. Until this is fixed, you can also view the pages through the Dev Center beta site

Regards,

3

This topic was automatically closed 30 days after the last reply. New replies are no longer allowed.