Text-to-Speech (TTS) is a speech synthesis technology that reads aloud the text you type in a human-like voice. A TTS engine converts the written text into audio. If you do not have a recorded audio file, type the required message. Automation supports TTS in messages for the Voice channel. You can use TTS in the supported languages. For the list of supported languages, see Supported languages.
To manage speech synthesis and text processing, you must mark the text with an appropriate tag. One message element can contain one tag. Automation supports the following tags:
Tags |
Description |
None |
A default option. Interprets the text as plain text. You can use special characters, excluding < (less than) and & (ampersand). |
Currency |
Interprets the text as a sum of money. Supports values that can be interpreted only as dollars and cents. For example, 1.50 is played as "one dollar and fifty cents". A TTS engine does not support international currency indicators, such as USD or CAD. |
Number |
Interprets the text as cardinal numbers. For example, 123 is played as "one hundred and twenty three". |
Digits |
Spells out each digit individually. For example, 123 is played as "one-two-three". |
Characters |
Spells out each letter of the text. For example, Hello is played as "H-E-L-L-O". |
Address |
Interprets the text as a street address. Type the full address according to your country standards. For example, specify a street, an estate number, a city, a state, and a zip code for the USA. |
