Speech synthesis

You can synthesise speech to your interlocutor before and during an active call or conference.

To synthesize speech during an inbound call, first answer a call. You can use the startEarlyMedia method to broadcast speech before the call is answered to create a greeting or a voicemail prompt.

To synthesize speech, use the call.say() method or the createTTSPlayer() method in your scenario. Pass the text string to synthesize in the first parameter and options in the second parameter. See the code example below to understand how it works:

Here is an example of the createTTSPlayer() method:

You can choose the voice for speech synthesis from one of these lists: VoiceList.Amazon, VoiceList.Google, VoiceList.Tinkoff, VoiceList.Yandex. The default voice is VoiceList.Amazon.en_US_Joanna.

If you have a custom Yandex engine voice, please contact support to activate this feature for your account, then specify the voice folder ID to the yandexCustomModelName property.

You can also configure other speech synthesis options, such as pitch, rate and volume. To specify them, list them in the ttsOptions parameter of the call.say() method or the createTTSPlayer() method. See the code example below:

The options have the following values:

If you want to set them for the whole text, you do not have to use the speak tag. If you want to use specific attributes for a part of the text, specify the speak tag manually.

For example, if we choose Amazon, we have to use the prosody tag to control volume, rate, or pitch of the selected text fragment. Here is how we make this fragment sound higher:

Here's another example of a specific Amazon's tag say-as: