Prerequisites
- Activate voice call:
- For SaaS installations, contact the support team to activate the feature.
- For on-premises installations, activate the feature by adding
FEATURE_ENABLE_VOICECALL_WHITELISTinvalues.yamland assigning the corresponding organization IDs. For example,FEATURE_ENABLE_VOICECALL_WHITELIST:<organization-1-id>,<organization-2-id>. For all organizations, use*.
- Configure a voice provider in the Project’s Voice Preview Settings and the AI Agent’s voice and language.
- Allow microphone access in your browser, and then in your device settings if needed.
- To target an AI Agent directly, create the AI Agent with a voice configuration first.
If the text-to-speech provider of the project is Amazon Polly, the call ignores the TTS Engine default of the Node. It uses the first engine that the selected voice supports, in this order: Standard, Neural, and Generative.
How to use voice call mode
To start a test call, click the- Monitor the call duration. The call header shows how long the call has been active, in the format
mm:ss, next to the locale. Until the call connects, the header shows Connecting…. To hide or show the call details, click Collapse call details or Expand call details. - Mute yourself. To stop sending your voice, click Mute. To continue, click Unmute.
- Send DTMF tones. Click
to open a dialpad and send touch-tone (DTMF) signals during the call. With the dialpad, you can enter codes or navigate menus during a call. - Follow the conversation. View the real-time conversation transcript in the interaction panel to track the call.