TTS Verbalization Guide and Specification for en-GB

Introduction

This document describes how a specific series of strings are read by the TTS Engine for the English language in the GB domain. All the specifications and usage are valid for the following solutions:

Voice Pack	Version	Release Date
en-GB Voice Pack	TBD	TBD

And for the TTS Engine version 2.8.0.

Numbers

Integers

Integers less than 1000

Format	Example
Format	Input String	Verbalized Form
[1-9][0-9]	31	thirty one
[1-9][0-9]…[0-9]	159	one hundred and fifty nine
<dash> [1-9]…[0-9]	-58	minus fifty eight

In en-GB, the word "and" is used after "hundred" (e.g., "one hundred and fifty nine").

Integers greater than 999

Allowed thousands delimiters

Comma
None

Space delimiter will result in two separate number groups.

Format	Example
Format	Input String	Verbalized Form
[1-9][0-9]…[0-9][0-9]	2824	two thousand eight hundred and twenty four
[1-9] <comma> [0-9] …[0-9][0-9]	2,824	two thousand eight hundred and twenty four
[1-9][0-9][0-9] <comma> [1-9][0-9][0-9] <comma> [1-9][0-9][0-9]	857,467,987	eight hundred and fifty seven million, four hundred and sixty seven thousand, nine hundred and eighty seven
[1-9][0-9][0-9][1-9][0-9][0-9][1-9][0-9][0-9]	857467987	eight hundred and fifty seven million, four hundred and sixty seven thousand, nine hundred and eighty seven
<dash> [1-9][0-9][0-9]…[0-9]	-12345	minus twelve thousand three hundred and forty five
<dash> [1-9][0-9][0-9] <comma> … <comma> [1-9][0-9][0-9]	-12,345	minus twelve thousand three hundred and forty five

Maximum supported value is 999 billions. Numbers greater than this will be spelled number by number.

Ordinal numbers

Format	Example
Format	Input String	Verbalized Form
[1-9]…[0-9]{st,nd,rd,th}	1st	first

Decimals

Allowed decimal separator

The individual numbers after the dot delimiter are spelled as single digits.

Format	Example
Format	Input String	Verbalized Form
[1-9]…[0-9] <dot> [0-9][0-9]…[0-9]	2.4527	two point four five two seven
<dash> [1-9]…[0-9] <dot> [0-9][0-9]…[1-9]	-25.78	minus twenty five point seventy eight

Number groups

Format	Example
Format	Input String	Verbalized Form
[0-9] <dash> … [0-9] <space> [0-9] <dash> … [0-9] <space> …	4-2-1-4 2-3-4 7-5-3	four two one, two three four, seven five three

16-digit card numbers

Card numbers belong to the number groups. In order to pronounce the 16-digit card number in groups of four digits with a short pause in between them, the input number has to contain the dashes, e.g.:

"Just to confirm, you said 5-8-9-7 4-2-6-5 1-2-3-4 7-4-6-8 9-7-2-6, correct?"

Input text in the format of: "5896 4265 1234 7468 9726"

will result in: "five thousand eight hundred and ninety six four thousand two hundred and sixty five,…"

Telephone numbers

Telephone numbers should be composed as number groups also. The following example:

"Your telephone number is 3-8-7 8-5-6 9-3-0."

would be read as "three eight seven <short pause> eight five six <short pause> nine three zero".

Combination of numbers and words

Format	Example
Format	Input String	Verbalized Form
[0-9] … [0-9] <dash> {word}	16-digit	sixteen digit
{word} <dash> [0-9] … [0-9]	COVID-19	covid nineteen

Beware of using spaces. When the dash sign is surrounded by space, it is verbalized as word "dash". For example, the verbalization of "16 - digit" is "sixteen dash digit".

Ratio

Format	Example
Format	Input String	Verbalized Form
[0-9] … [0-9] <colon> [0-9] … [0-9]	16:9	sixteen to nine
[0-9] … [0-9] <dash> [0-9] … [0-9]	16-9	sixteen to nine

Percentage

Format	Example
Format	Input String	Verbalized Form
[1-9]…[0-9] <percent sign>	15%	fifteen percent

Time

Format	Example
Format	Input String	Verbalized Form
[00-99] <colon> [00-59] <colon> [00-59]	12:11:01	twelve hours ten minutes and one second
[00-24] <colon> [00-59]	23:15	twenty three fifteen
[1-12] <space> {PM, AM}	2 PM	two p m
[1-12] <space> {P.M., A.M.}	2 P.M.	two p m
[0-12] <colon> [0-59] <space> {PM, AM}	02:20 PM	two twenty p m
[0-12] <colon> [0-59] <space> {P.M., A.M.}	02:20 P.M.	two twenty p m
00:00	00:00	midnight

Time Intervals

Format	Example
Format	Input String	Verbalized Form
[0-9] … [0-9] <dash> [1-9] … [0-9] <space> {days, hours, months, minutes}	3-5 days	three to five days

Date

Format	Example
Format	Input String	Verbalized Form
[1-31] <space> {month} <space> [0-9][0-9][0-9][0-9]	14 May 2022	the fourteenth of may twenty twenty two
[1-31] <space> {month}	14 May	the fourteenth of may
{month} <space> [1-31] <comma> <space> [1-9][0-9][0-9][0-9]	June 6, 2020	the sixth of june twenty twenty
{month} <space> [1-31]	June 6	the sixth of june
[00-31] <slash> [00-12] <slash> [1-9][0-9]	31/12/19	the thirty first of december twenty nineteen
[00-12] <slash> [00-31] <slash> [1-9][0-9]	12/31/22	the thirty first of december twenty twenty two
[00-31] <dash> [00-12] <dash> [1-9][0-9][0-9][0-9]	27-05-2021	the twenty seventh of may twenty twenty one
[00-31] <dot> [00-12] <dot> [1-9][0-9][0-9][0-9]	27.05.2021	the twenty seventh of may twenty twenty one
[0-31] <dot> [0-12] <dot> [1-9][0-9][0-9][0-9]	27.5.2021	the twenty seventh of may twenty twenty one
[1-9][0-9][0-9][0-9] <dash> [00-12] <dash> [00-31]	2022-11-02	the second of november twenty twenty two
[00-31] <slash> [00-12]	05/12	the fifth of december
{month}<space> [1-31]{st,nd,rd,th}	October 21st	october the twenty first

In en-GB, dates are verbalized with "the" before ordinals and "of" before the month when following the day-first pattern (e.g., "the fourteenth of may"). When month comes first, "the" is placed before the ordinal (e.g., "october the twenty first"). The slash-separated date format follows DD/MM/YY(YY) convention in en-GB.

Units

Format	Example
Format	Input String	Verbalized Form
{amount} {unit}	2.5GB	two point five gigabytes
{amount} <space> {unit}	3 m	three metres
{amount} {unit} <slash> {unit}	1500MB/s	one thousand five hundred megabytes per second
{amount} <space> {unit} <slash> {unit}	1 km/h	one kilometre per hour

Unit

Abbreviation	Verbalization	Abbreviation	Verbalization
mm	millimetre(s)	cm	centimetre(s)
m	metre(s)	km,Km	kilometre(s)
m²,m2	square metre(s)	m³,m3	cubic metre(s)
",in	inch(es)	ft	foot(feet)
yd	yard(s)	mi	mile(s)
mph,MPH	mile(s) per hour	h,hr	hour(s)
min,mins	minute(s)	s	second(s)
g,gm	gram(s)	kg,Kg	kilogram(s)
oz	ounce(s)	lb,lbs	pound(s)
ml,mL	millilitre(s)	cl,cL	centilitre(s)
l,L	litre(s)	gal	gallon(s)
Hz,hz	hertz	kHz,KHz,khz	kilohertz
MHz	megahertz	GHz,Ghz,ghz	gigahertz
mW	milliwatt(s)	w,W	watt(s)
kW,KW	kilowatt(s)	MW	megawatt(s)
GW	gigawatt(s)	kwh,kWh,KWh	kilowatt(s) hour
v,V	volt(s)	mA	milliampere(s)
A	ampere(s)	db,dB	decibel(s)
kb,Kb,kbit	kilobit(s)	mb,Mb,Mbit	megabit(s)
gb,Gb,Gbit	gigabit(s)	tb,Tb,Tbit	terabit(s)
pb,Pb,Pbit	petabit(s)	bps	bit(s) per second
Kbps	kilobit(s) per second	Mbps	megabit(s) per second
Gbps	gigabit(s) per second	Tbps	terabit(s) per second
kB,KB	kilobyte(s)	MB	megabyte(s)
GB	gigabyte(s)	TB	terabyte(s)
PB	petabyte(s)	kBps,KBps	kilobyte(s) per second
MBps	megabyte(s) per second	GBps	gigabyte(s) per second
TBps	terabyte(s) per second	PBps	petabyte(s) per second
°C,°c	degree(s) celsius	°F,°f	degree(s) fahrenheit

Words

Abbreviations and Spelling

Format	Example
Format	Input String	Verbalized Form
[A-Z] … [A-Z]	ABC	a b c
[A-Z] <dot> [A-Z] <dot> … [A-Z] <dot>	B.C.	b c
[a-z] <dot> [a-z] <dot> … [a-z] <dot>	e.g.	for example
[a-zA-Z] & [a-zA-Z]	R&D	r-n-d
[a-zA-Z] , like [a-zA-Z]	a, like alpha	A, like alpha
{common abbreviation}	Dr.	doctor
<space> [A-Z] {<comma>, <dot>, <space>}	A or B	a or b

All the capitalized letters are supposed to be spelled.

Common abbreviation

Abbreviation	Verbalization	Abbreviation	Verbalization
Prof.	professor	Mr.	mister
Dr.	Doctor	Mrs.	Misses
e.g.	for example	Ms.	miss
etc.	and so on	Jr.	junior
Inc.	incorporated	Co.	company
Ph.d	P H D	Sr.	senior
hon.	honourable	Pres.	President
Gov.	Governor	Lt.	Lieutenant
Col.	Colonel	Gen.	General
corp.	corporation	Univ.	university
assn.	association	Dept.	department
ave.	avenue	rd.	road
st.	street	blvd.	boulevard
ln.	lane	vs.	versus
ft.	foot	in.	inch
lb.	pound	oz.	ounce
gal.	gallon	pt.	pint
qt.	quart	cu.	cubic
sq.	square	hr.	hour
min.	minute	sec.	second
yr.	year	mo.	month
wk.	week	no.	number
pg.	page	vol.	volume
vol.	volume	ed.	edition
rev.	revised	trans.	translated
pub.	published	ltd.	limited
govt.	government	inst.	institute
acad.	academy	soc.	society
bros.	brothers	mfg.	manufacturing
natl.	national	intl.	international
org.	organisation	temp.	temperature
approx.	approximately	prelim.	preliminary
prov.	province	jan.	January
feb.	February	mar.	March
apr.	April	jun.	June
jul.	July	aug.	August
sept.	September	oc.	October
nov.	November	dec.	December
mon,	Monday	tue.	Tuesday
wed.	Wednesday	thu.	Thursday
fri.	Friday	sat.	Saturday
sun.	Sunday	attn	attention
attn.	attention	attn:	attention
P0	P 0	P.0.	P 0

Dashed words

Format	Example
Format	Input String	Verbalized Form
[a-Z] … [a-z] <dash> [a-Z] … [a-z]	E-mail	e mail
[a-Z]…[a-z] <space> <dash> <space> [a-Z] … [a-z]	Paris - Texas	paris dash texas

URLs and E-mails

Format	Example
Format	Input String	Verbalized Form
(www) <dot> {word} <dot> {domain}	www.google.com	w w w dot google dot com
(www) <dot> {word} <dot> {domain} <forward slash> {path}	www.google.com/maps	w w w dot google dot com forward slash maps
{protocol} <colon> <forward slash> <forward slash> {word} <dot> {domain}	https://google.com	h t t p s colon forward slash forward slash google dot com
{protocol} <colon> <forward slash> <forward slash> {word} <dot> {domain} <forward slash> {word} <hyphen> {word}	https://www.example.com/my-page	h t t p s colon forward slash forward slash w w w dot example dot com forward slash my hyphen page
{protocol} <colon> <forward slash> <forward slash> {word} <dot> {domain} <colon> {port} <forward slash> {path}	http://example.com:8080/path/to/resource	h t t p colon forward slash forward slash example dot com colon eight thousand and eighty forward slash path forward slash to forward slash resource
{protocol} <colon> <forward slash> <forward slash> {ip} <forward slash> {path}	http://123.123.123.123/path/to/resource	h t t p colon forward slash forward slash one hundred and twenty three dot one hundred and twenty three dot one hundred and twenty three dot one hundred and twenty three forward slash path forward slash to forward slash resource
{protocol} <colon> <forward slash> <forward slash> {word} <dot> {domain} <forward slash> {path} <percent> {encoded}	http://example.com/path%20with%20spaces	h t t p colon forward slash forward slash example dot com forward slash path percent two zero with percent two zero spaces
{protocol} <colon> <forward slash> <forward slash> {word} <dot> {domain} <forward slash> {word} <equal sign> <question mark> {query}	https://www.ocp.ai/input=?$ad	h t t p s colon forward slash forward slash w w w dot ocp dot ai forward slash input equal sign question mark dollar sign ad
ftp <colon> <forward slash> <forward slash> ftp <dot> {word} <dot> {domain} <forward slash> {path}	ftp://ftp.example.com/resource	f t p colon forward slash forward slash f t p dot example dot com forward slash resource
{word} <at sign> {word} <dot> {domain}	info@google.com	i n f o at google dot com

Note: In all English locales, the following characters are verbalized in URLs and email addresses:

Character	Verbalization
.	dot
@	at
/	forward slash
-	hyphen
:	colon
_	underscore
=	equal sign
?	question mark
%	percent
$	dollar sign

Currency

Format	Example
Format	Input String	Verbalized Form
{currency symbol} {amount}	$25.10	twenty five dollars and ten cents
	£25,000	twenty five thousand pounds
{amount} {currency symbol}	25.10€	twenty five euros and ten cents
{amount} <space> {currency code}	25 USD	twenty five us dollars
{currency code} <space> {amount}	GBP 25	twenty five pounds sterling
{currency code} {amount} <space> {quantity}	$1.3 million	one point three million dollars
{amount} <space> {quantity} <space> {currency code}	1 million USD	one million us dollars

Currency code

Code	Verbalized form	Subdivision
USD	u s dollar(s)	cent(s)
EUR	euro(s)	cent(s)
GBP	pound(s) sterling	penny, pence

Currency symbol

Symbol	Verbalized form
$	dollar(s)
€	euro(s)
£	pound(s)

Amount examples

Amount	Verbalized form
$235,125,250.12	two hundred and thirty five million, one hundred and twenty five thousand, two hundred and fifty dollars and twelve cents
$3.458	three point four five eight dollars
$5,000.00	five thousand dollars
$0.01	one cent
$-0.01	minus one cent
£1,250.99	one thousand two hundred and fifty pounds and ninety nine pence
£0.01	one penny

Quantity

million
billion
trillion

Punctuation and Characters Processing

Supported characters

Char	Description	Used as/in	Char	Description	Used as/in
.	period	sentence ending	@	at sign	email address
	decimal separator	-	dash	number group
,	comma	sentence break		word group
	thousands separator		minus sign
?	question mark	sentence ending	+	plus sign	math equation
!	exclamation mark	sentence ending	$	dollar sign	part of currency
'	apostrophe	contraction	€	euro sign	part of currency
	possessive noun	£	pound sign	part of currency
%	percent sign	percentage value	&	ampersand	and (except for the R&D like cases)

Other characters or punctuation will be removed and will not affect the voice.

Punctuation

If no punctuation is present in the input text, the period will be added automatically. There is no check of the sentence content or a type in order to distinguish the punctuation.

Thank you for using our service → Thank you for using our service.

What can I do for you → What can I do for you.

Char	Description	Effect
.	period	falling intonation
?	question mark	raising intonation
	space	pause
	dash	short pause
,	comma	falling intonation
!	exclamation mark	increased intensity

The question mark does not always result in rising intonation. It follows the question intonation rules of en-GB referring to rising, falling and rise-fall intonation for yes/no, wh- or multiple choice questions.

Examples

This section illustrates the examples of common prompts and verbalization usage.

Input:

"Welcome to voice-enabled service line of ABC Bank! What can I do for you today?"

Verbalized output:

"welcome to voice enabled service line of a b c bank ! what can I do for you today ?"

Input:

"Ok, first, please say or enter your 16-digit card number."

Verbalized output:

"ok , first , please say or enter your sixteen digit card number ."

Input:

"Just to confirm, you said: 5-8-9-7 4-2-6-5 1-2-3-4 7-4-6-8 9-7-2-6."

Verbalized output:

"just to confirm , you said five eight nine seven , four two six five , one two three four , seven four six eight , nine seven two six ."

Input:

"The balance on your visa is $2670.52 and it is due the 21st of March. Anything else?"

Verbalized output: "the balance on your visa is two thousand six hundred and seventy dollars and fifty two cents and it is due the twenty first of march . anything else ?"

Input:

"Your email is cadomaitis@omilia.com. Is that correct?"

Verbalized output:

"your email is c a d o m a i t i s at o m i l i a dot com. is that correct?"

Input:

"To confirm, Your appointment will be set for Tuesday, the 25th of October, 09:00 to 10:30 AM. Shall I proceed?"

Verbalized output:

"to confirm, your appointment will be set for tuesday , the twenty fifth of october, nine to ten thirty a m . shall I proceed ?"

Input:

"The balance on your mastercard is -1.35 USD. The debt has to be paid until the 2nd of November 2022."

Verbalized output:

"the balance on your mastercard is minus one u s dollar and thirty five cents . the debt has to be paid until the second of november twenty twenty two ."

Input:

"Please visit www.omilia.com/support for more information."

Verbalized output:

"please visit w w w dot omilia dot com forward slash support for more information ."