Text to Speech (TTS), also known as speech synthesis, is a technology that converts text into a human-like voice. Both developers and business users utilize TTS to transform traditional human-to-human interactions into seamless machine-to-human experiences, ensuring every voice interaction is smooth and high-quality.

Instead of using pre-recorded human voices, which offer limited flexibility and scalability, TTS allows for dynamic, programmatically generated prompts from raw text in response to application events. Whether for Interactive Voice Response (IVR) systems, conversational assistants in contact centers, or voice notifications delivering critical messages via phone calls, TTS enhances efficiency on a global scale and improves customer engagement.

Text To Speech voices overview

Naxai Text To Speech offers various voices in multiple languages and locales with associated accents and pronunciations. Naxai strongly partners with Acapela Group, providing the best TTS locales for countries like Belgium to support Dutch and Belgian French.

Based on Acapela Neural TTS, AI-generated voices are highly realistic. They enhance user engagement and experience.

These voices are generated using the latest technology and innovation in synthesized speech, providing the most human-like, expressive, and natural-sounding text-to-speech voices possible, with higher quality than Standard voices.

Available voices and languages

The following table contains all voices available for each language and locale.

👍

Contact our Support Team if you language is not yet supported.

Text To Speech Tips

Punctuation Characters

Comma, colon and semicolon

Comma ',', colon ':' and semicolon ';' cause a brief pause to occur in a sentence,
accompanied by a small rising intonation pattern just prior to the character.

Quotation marks

Closing quotes '“”' after a single word or a group of words cause a brief pause after
the quoted text.

Full stop

A full stop '.' is a sentence terminal punctuation mark which causes a falling end-of-
sentence intonation pattern and is accompanied by a somewhat longer pause. A full
stop may also be used as a decimal marker in a number and in abbreviations.

Question mark

A question mark '?' ends a sentence and causes question-intonation, first rising and
then falling.

Exclamation mark

The exclamation mark '!' is treated in a similar manner to the full stop, causing a
falling intonation pattern followed by a pause.

Parentheses, brackets and braces

Parenthesis '()', brackets '[]' and braces '{}' appearing around a single word or a
group of words cause a brief pause before and after the bracketed text.

Non-punctuation characters

The characters listed below are processed as non-letter, non-punctuation characters.
Some are pronounced at all times and others only in certain
contexts.

Currency amounts

The following principles are followed for currency amounts:

• Numbers with zero, one, or two decimals preceded or followed by the
  currency markers £, $, ¥ or € are read as currency amounts.
• Numbers with zero, one or two decimals followed by the words
  livre, dollar, yen or euro (singular or plural) are read as currency amounts.
• Accepted decimal markers are comma ',' and full stop '.'.
• The decimal part (consisting of one or two digits) in currency amounts is
  read as "et nn pence", "et nn cents" and "et nn centimes" in French.
• If the decimal part is 00 it will not be read.

Examples in French

$15.00 -> quinze dollars
15.00£ -> quinze livres
15.00 euro -> quinze euros
€ 200.50 -> deux cents euros et cinquante centimes

Time of day

The colon is used to separate hours, minutes and seconds. When there are no
seconds, H or h can be used to separate hours and minutes.

Abbreviations such as A.M. and P.M. may follow or precede the time.

Possible patterns are:
a. hh:mm or h:mm
b. hh:mm:ss or h:mm:ss
c. hhHmm or hHmm
h = hour, m = minute, s = second.
If the mm-part equals 00, this part will not be read.

Example in French

9:00 -> neuf heures
9:30 P.M. -> neuf heures trente du soir

Dates

The valid formats for dates are:

• dd-mm-yyyy, dd.mm.yyyy, and dd/mm/yyyy
• dd-mm-yy, dd.mm.yy, and dd/mm/yy

yyyy is a four-digit number, yy is a two-digit number, mm is a month number
between 1 and 12 and dd a day number between 1 and 31. Hyphen, full stop, and
slash may be used as delimiters. In all formats, one or two digits may be used in the
mm and dd part. Zeros may be used in front of numbers below 10.

When using Voice Broadcast with a date stored in a contact attribute, you can use Liquid Syntax to manipulate the data and format it to the above-supported format.