Prerequisites
- Configure a speech provider in Manage > AI & Voice Providers. For more information, see Speech and telephony.
- Access to Voice.
- Configure a Flow.
- For testing purposes, allow microphone access in your browser and, if needed, in your device settings.
Restrictions
- The Click To Call widget doesn’t support DTMF input by default. If you build your own interface with the Click To Call SDK, you can send DTMF tones with
sendDTMF(). - Click To Call supports only the Dial transfer type for call transfers.
Configure a Click To Call widget
Configure the widget
Configure the widget
To embed a Click To Call widget into your website, follow these steps:
- In Deploy > Endpoints, click + New Endpoint and select Voice.
- In the New Endpoint section, configure the following:
- Name — enter a unique name.
- Flow — select a Flow you previously created.
- Go to the Click To Call tab. In the Appearance section, configure the following:
- Activate Click To Call widget — turn on the toggle.
- Voice agent name — enter the name displayed on the Click To Call widget, for example,
Package Support. - Subtitle — enter the text displayed under the voice agent name on the widget, for example,
Get help with your package. - Avatar URL — URL of the image to be displayed on the widget, for example,
https://www.<domain>.com/logo.png. If the field is empty or the URL is invalid, the widget uses the default AI icon. - (Optional) Theme — select the color theme of the widget: Clean white, Dark mode (default), or AI purple.
- In the Transcription customization section, turn on Show live transcription to show the conversation transcript in the widget.
- Save the Endpoint. The Embedding HTML section on the same tab contains the code to embed the widget in your website.
(Optional) Configure a privacy notice
(Optional) Configure a privacy notice
In the Privacy notice section of the Click To Call tab in the Voice endpoint settings, you can add a privacy notice with the following parameters: