TTS Verbalization Guide & Specifications for pt-BR

Product: pt-BR
Release Date: October 2026
TTS Engine version: 3.4.0

Introduction

This document describes how specific series of strings are read by the TTS Engine for the PTlanguage in the BR domain. Example outputs are in Portuguese (Brazilian Portuguese). The readings are the engine's current output for the version above: when a reading is not what is wanted, this document still shows what the engine does.

Convention: every example table includes a Lexis voice output column. Any new row appears marked with 🆕. Missing support is shown as "unsupported". Numeric ranges use [a-b] (for example, [1-99] means any number from 1 to 99).

Readings are shown in lower case with punctuation as the engine returns it. Two markers appear in the readings: [pause] is a 0.025 s pause the Lexis voice puts between groups of digits, and [pause 0.2 s] is a fixed pause of 0.2 s.

Numbers

Integers

Format	Example input	Lexis
`[1-9][0-9]`	`25`	vinte e cinco
`[1-9][0-9]…[0-9]`	`159`	cento e cinquenta e nove
`100`	`100`	cem
`10[1-9]`	`101`	cento e um
`<dash>[1-9]…[0-9]`	`-58`	menos cinquenta e oito
`[1-9][0-9]…[0-9][0-9] (>999)`	`2824`	dois mil oitocentos e vinte e quatro
`[1-9][0-9]{3}`	`1500`	mil e quinhentos
`[1-9][0-9]{0,2}<dot>[0-9]{3}`	`2.824`	dois mil oitocentos e vinte e quatro
`1000000`	`1.000.000`	um milhão
`2000000`	`2.000.000`	dois milhões
`1000000000`	`1.000.000.000`	um bilhão

Allowed thousands delimiter: dot (a space is read the same way). Max supported value: 999.999.999.999, read as "novecentos e noventa e nove bilhões novecentos e noventa e nove milhões novecentos e noventa e nove mil novecentos e noventa e nove". Beyond that, digits are spelled one by one.

Ordinal numbers

Format	Example input	Lexis
`[1-9]…[0-9]{º}`	`1º`	primeiro
`[1-9]…[0-9]{ª}`	`1ª`	primeira
`[1-9]…[0-9]{º}`	`21º`	vigésimo primeiro

Decimals

Decimal separator: comma. Digits after the comma are spelled individually ("2,4527"); a two-digit fraction is read as a number ("-25,78" is "menos vinte e cinco vírgula setenta e oito").

Format	Example input	Lexis
`[1-9]…[0-9]<comma>[0-9]…[0-9]`	`2,4527`	dois vírgula quatro cinco dois sete
`<dash>[1-9]…[0-9]<comma>[0-9]…[0-9]`	`-25,78`	menos vinte e cinco vírgula setenta e oito

Fractions and units

Format	Example input	Lexis
`[1-99]<slash>[1-99]`	`13/16`	treze dezesseis avos
`[1-99]<slash>[1-99]`	`45/2`	quarenta e cinco meios
`[1-99]<slash>[1-99]`	`3/4`	três de abril

A fraction that complies with the date format, thus [1-31]<slash>[1-12], is read as a date if no supported unit is provided. E.g. "5/12" is read as "cinco de dezembro" while "5/12 km" is read as "cinco doze avos de quilômetro". Because dates are day first, fractions such as 3/4 and 1/2 are read as dates ("três de abril", "primeiro de fevereiro").

Format	Example input	Lexis
`{vulgar fraction} <unit>`	`½ xícara`	½ xícara
`[1-99]/[1-99] <unit>`	`3/4 mi`	três de abril mi
`[1-31]<slash>[1-12] <unit>`	`5/12 km`	cinco doze avos de quilômetro

A vulgar fraction such as ½ is not converted: the text passes through unchanged.

Digit-by-digit spelling

The dash notation can be used to spell the digit sequence digit by digit. For Lexis, the digits of a group are separated by a comma and the groups are separated by a space.

Example input	Lexis
`4-2-1-4 2-3-4 7-5-3`	quatro dois um [pause] quatro, dois três [pause] quatro, sete cinco [pause] três

Note: a dash between two numbers is read digit by digit, but in case of range or match score, will be read as ("2-3" is "dois a três").

16-digit card numbers

Example input	Lexis
`5-8-9-6 4-2-6-5 1-2-3-4 7-4-6-8`	cinco oito nove [pause] seis, quatro dois [pause] seis cinco, um [pause] dois três quatro, [pause] sete quatro seis [pause] oito
`5-8-9-6-4-2-6-5 1-2-3-4-7-4-6-8`	cinco oito nove [pause] seis quatro dois [pause] seis cinco, um [pause] dois três quatro [pause] sete quatro seis [pause] oito

Counter examples

A dash between the groups of digits is read digit by digit as well: the numbers in between are not read as integers and the dash is not pronounced.
If no dash is used, the numbers are read as integers.

Example input	Lexis
`4532-1234-5678-9012`	quatro mil quinhentos e trinta e dois traço mil duzentos e trinta e quatro traço cinco mil seiscentos e setenta e oito traço nove mil e doze
`4532 1234 5678 9012`	quatro mil quinhentos e trinta e dois mil duzentos e trinta e quatro cinco mil seiscentos e setenta e oito nove mil e doze
`4532-1234-5678`	quatro mil quinhentos e trinta e dois traço mil duzentos e trinta e quatro traço cinco mil seiscentos e setenta e oito
`4532-1234`	quatro mil quinhentos e trinta e dois a mil duzentos e trinta e quatro

Telephone numbers

Format	Example input	Lexis
`([0-9]{2}) 9[0-9]{4}-[0-9]{4}`	`(11) 91234-5678`	onze, nove um dois três quatro, cinco meia sete oito
`([0-9]{2}) [0-9]{4}-[0-9]{4}`	`(11) 3456-7890`	onze, três quatro cinco meia, sete oito nove zero
`+[0-9]{2} ([0-9]{2}) 9[0-9]{4}-[0-9]{4}`	`+55 (11) 91234-5678`	mais cinquenta e cinco, onze, nove um dois três quatro, cinco meia sete oito

The area code is read as a number when it has two digits, the groups are read digit by digit with commas between them, and 6 is read "meia".

Combination of numbers and words

Format	Example input	Lexis
`[0-9]…[0-9]<dash>{word}`	`16-bit`	dezesseis bit
`{word}<dash>[0-9]…[0-9]`	`COVID-19`	covid dezenove

A space around a dash between a number and a word verbalizes the dash as the word "traço" (e.g. "16 - bit" becomes "dezesseis traço bit"). A spaced dash between two words is read as a pause (see Dashed words).

Ratio and intervals

Format	Example input	Lexis
`[0-9]…[0-9]<colon>[0-9]…[0-9]`	`16:9`	dezesseis por nove
`[0-9]…[0-9]<dash>[0-9]…[0-9]`	`16-9`	dezesseis a nove
`[0-9]…[0-9]<dash>[0-9]…[0-9] {word}`	`3-5 dias`	três a cinco dias

If the ratio values overlap with the time format, the time will be announced. E.g. "24:00" is verbalized as "meia noite" while "25:00" is "vinte e cinco por zero". A ratio is read with "por" ("16:9" is "dezesseis por nove"). A dash between two numbers is read digit by digit, except before a word.

Percentage

Example input	Lexis
`15%`	quinze por cento
`2,5%`	dois vírgula cinco por cento

Time

Format	Example input	Lexis
`[00-24]<colon>[00-59]<colon>[00-59]`	`12:11:01`	doze horas onze minutos e um segundo
`[00-24]<colon>[00-59]`	`23:15`	vinte e três e quinze
`[00-24]h[00-59]`	`14h30`	14h30
`[00-24]<colon>00`	`24:00`	meia-noite
`12<colon>00`	`12:00`	meio-dia
`00<colon>00`	`00:00`	meia-noite
`[1-12] {PM,AM}`	`2 PM`	duas horas da tarde
`[01-12]<colon>[00-59] {PM,AM}`	`02:20 PM`	duas e vinte da tarde

Note: a whole PM or AM hour is read with "horas" ("2 PM" is "duas horas da tarde") and with minutes without it ("02:20 PM" is "duas e vinte da tarde"); "14h30" is left as written.

Date

Format	Example input	Lexis
`[2-31] de {month} de [0-9]{4}`	`14 de maio de 2022`	quatorze de maio de dois mil e vinte e dois
`1 de {month} de [0-9]{4}`	`1 de junho de 2020`	um de junho de dois mil e vinte
`[00-31]/[00-12]/[0-9][0-9]`	`31/12/19`	trinta e um de dezembro de dezenove
`[00-31].[00-12].[0-9]{4}`	`27.05.2021`	vinte e sete de maio de dois mil e vinte e um
`[0-9]{4}-[00-12]-[00-31]`	`2022-11-02`	dois de novembro de dois mil e vinte e dois
`[1-31] de {month}`	`21 de outubro`	vinte e um de outubro
`[1-31]/[1-12]`	`23/5`	vinte e três de maio
`[1-31]/[1-12]`	`5/12`	cinco de dezembro

Note: Dates are day first, so "5/12" is the 5th of December (en-US reads May 12th). A two-digit year after a date is read as a number ("dezenove"); a full year is read as one number ("dois mil e vinte e dois").

Units

Format	Example input	Lexis
`{amount}{unit}`	`2,5GB`	dois vírgula cinco gigabytes
`{amount}<space>{unit}`	`1,5 GB`	um vírgula cinco gigabytes
`{amount}{unit}/{unit}`	`1500MB/s`	mil e quinhentos megabytes por segundo
`{amount}<space>{unit}/{unit}`	`1400 MB/s`	mil e quatrocentos megabytes por segundo

Supported unit abbreviations

Each reading shows the singular / the plural form: the unit is read after "1" and after "2". The readings come from the Portuguese unit table of the input processor tests.

Abbreviation	Lexis
`mm`	milímetro / milímetros
`cm`	centímetro / centímetros
`m`	metro / metros
`km`	quilômetro / quilômetros
`Km`	quilômetro / quilômetros
`m²`	metro quadrado / metros quadrados
`m2`	metro quadrado / metros quadrados
`m³`	metro cúbico / metros cúbicos
`m3`	metro cúbico / metros cúbicos
`"`	"
`in`	in
`'`	'
`ft`	ft
`yd`	yd
`mi`	mi
`mph`	mph
`MPH`	mph
`h`	hora / horas
`hr`	hora / horas
`min`	minuto / minutos
`mins`	mins
`s`	segundo / segundos
`g`	grama / gramas
`gm`	gm
`kg`	quilograma / quilogramas
`Kg`	quilograma / quilogramas
`oz`	oz
`lb`	lb
`lbs`	lbs
`ml`	mililitro / mililitros
`mL`	mililitro / mililitros
`l`	litro / litros
`L`	litro / litros
`gal`	gal
`cup`	cup
`Hz`	hertz
`hz`	hz
`kHz`	quilohertz
`MHz`	megahertz
`GHz`	gigahertz
`W`	watt / watts
`kW`	quilowatt / quilowatts
`MW`	megawatt / megawatts
`GW`	gw
`V`	volt / volts
`mA`	miliampere / miliamperes
`A`	ampere / amperes
`dB`	decibel / decibéis
`kb`	kb
`mb`	mb
`gb`	gb
`tb`	tb
`pb`	pb
`kB`	kilobyte / kilobytes
`MB`	megabyte / megabytes
`GB`	gigabyte / gigabytes
`TB`	terabyte / terabytes
`PB`	petabyte / petabytes
`bps`	bit por segundo / bits por segundo
`Kbps`	kilobit por segundo / kilobits por segundo
`Mbps`	megabit por segundo / megabits por segundo
`Gbps`	gigabit por segundo / gigabits por segundo
`Tbps`	tbps
`kBps`	kbps
`MBps`	mbps
`GBps`	gbps
`TBps`	tbps
`PBps`	pbps
`°C`	grau celsius / graus celsius
`°c`	° c
`°F`	grau fahrenheit / graus fahrenheit
`°f`	° f

Note: Short abbreviations that are also words or letters (in, min, h, m, A, s) are read as units only when they follow a number; "in" is not a unit here ("5 in the box" is left as written).

Words

Abbreviations and spelling

Lexis passes words in capital letters through unchanged and the Lexis model reads them (e.g. ABC, JOHN). Dotted capital abbreviations keep their dots (e.g. B.C.).

Format	Example input	Lexis
`[A-Z]…[A-Z]`	`ABC`	abc
`[A-Z]…[A-Z]`	`JOHN`	john
`[A-Z]<dot>[A-Z]<dot>`	`B.C.`	b. c
`[A-Z]&[A-Z]`	`P&D`	p&d

Between capital letters, "&" is passed through. Between words, "&" is read as "e".

A single letter is read by its letter name: F is "efe", R is "érre", W is "dáblio".

Common abbreviations

Example input	Lexis
`Prof.`	professor
`Prof.ª`	prof. ª
`Dr.`	doutor
`Dra.`	doutora
`Sr.`	senhor
`Sra.`	senhora
`etc.`	etcétera

Dashed words

Example input	Lexis
`guarda-chuva`	guarda-chuva
`e-mail`	e-mail
`Rio - Niterói`	rio [pause 0.2 s] niterói
`Rio-Niterói`	rio-niterói

URLs and e-mails

URLs

Format	Example input	Lexis
`(www)<dot>{word}<dot>{domain}`	`www.google.com`	dáblio dáblio dáblio, ponto google, ponto com
`http(s)://{word}<dot>{domain}`	`http://google.com`	agá tê tê pê, dois pontos, barra barra google, ponto com
`http(s)://www<dot>{word}<dot>{domain}`	`https://www.google.com`	agá tê tê pê ésse, dois pontos, barra barra dáblio dáblio dáblio, ponto google, ponto com
`(http(s)://)(www)<dot>{word}<dot>{domain}<slash>{sequence}`	`https://www.google.com/news=123`	agá tê tê pê ésse, dois pontos, barra barra dáblio dáblio dáblio, ponto google, ponto com, barra ene é dáblio ésse, igual um dois três
`(http(s)://)(www)<dot>{non-word}<dot>{domain}`	`www.123.com`	dáblio dáblio dáblio, ponto um dois três, ponto com

E-mails

Format	Example input	Lexis
`{word}@{word}<dot>{domain}`	`info@omilia.com`	info, arroba omilia, ponto com

Currency

Format	Example input	Lexis
`R${amount}`	`R$25,10`	vinte e cinco reais e dez centavos
`{symbol}{amount}`	`$25,10`	vinte e cinco dólares e dez centavos
`{amount}{symbol}`	`25,10€`	vinte e cinco euros e dez centavos
`{amount} {code}`	`25 USD`	vinte e cinco dólares americanos
`{amount} {quantity} {code}`	`1,3 milhões USD`	um vírgula três milhões de dólares americanos
`{symbol}{amount} {quantity}`	`$1,3 milhões`	um vírgula três milhões de dólares

Note: after "milhão/milhões" the noun is introduced by "de" ("um vírgula três milhões de dólares").

Currency codes and symbols

Each reading shows the singular / the plural form. The subdivision is read after "e" when the amount has decimals ("1,01" and "2,50").

Code	Lexis	Subdivision
`USD`	dólar americano / dólares americanos	centavo / centavos
`EUR`	euro / euros	centavo / centavos
`GBP`	libra esterlina / libras esterlinas	pêni / pence
`AUD`	dólar australiano / dólares australianos	centavo / centavos
`CAD`	dólar canadense / dólares canadenses	centavo / centavos
`JPY`	iene / ienes	none: `1,50 JPY` reads um vírgula cinquenta iene
`BRL`	real / reais	centavo / centavos

Symbol	Lexis
`$`	dólar / dólares
`€`	euro / euros
`£`	libra esterlina / libras esterlinas
`¥`	iene / ienes
`R$`	real / reais

Punctuation and character processing

Supported characters

Char	Description	Used as/in	Lexis
`.`	period	sentence end / thousands separator	✅
`,`	comma	sentence break / decimal separator	✅
`-`	dash	number group / minus sign	✅
`@`	at sign	email address	✅
`%`	percent	percentage value, in URLs	✅
`&`	ampersand	"e" (between capital letters it is passed through)	✅
$ € £ ¥ R$	currency signs	part of currency	✅
`=`	equal sign	in URLs	✅
`;`	semicolon	in URLs	✅
`? !`	question mark, exclamation mark	sentence end (see intonation)	✅
`: / ( )`	colon, slash, brackets	time, ratio, URLs, fractions, dates	✅
`° ² ³ " '`	degree, superscripts, quotes	units	✅
`º ª`	ordinal indicators	ordinal numbers	✅

The slash is read "barra". Other symbols are read by name: \ "barra invertida", ^ "circunflexo", _ "sublinhado", + "mais", # "cerquilha", $ "cifrão", * "asterisco" and ~ "til". Outside times, ratios and URLs a colon or semicolon is replaced by a full stop, and brackets are passed on unchanged. The vulgar fraction ½ is not converted.

Any other character has no reading of its own: the processor passes it on unchanged (for example quotation marks and ©, ®, ™, §, ×, ÷, ±).

Punctuation intonation

Char	Lexis effect
`.`	falling intonation
`?`	rising intonation for yes/no questions
`,`	falling intonation
`!`	a lone exclamation mark is rewritten as a full stop (falling intonation)
space / dash	short pause (a spaced dash is a fixed pause of 0.2 s)
no punctuation at the end of a sentence	a period is added automatically