English Phonemes

The tables below list the full set of phonemes supported by Capacity Private Cloud Neural and LLM TTS for English. Five regional variants are covered: American English (en-US), British English — England (en-GB), British English — Scotland (en-GB), British English — Wales (en-GB), and English (Ireland) (en-IE). Each phoneme is shown with its Unicode code point(s), decimal value(s), IPA symbol, X-SAMPA representation, viseme, and an example word. Consonants and vowels are listed separately.

Phonemes can be supplied in SSML using the <phoneme> element (with alphabet="ipa" or alphabet="x-sampa") to override the default pronunciation of a word. For the complete list of Neural TTS voices, see Neural TTS Languages.

American English — en-US

These phonemes apply to the following American English Neural TTS voices:

Adam
Jeff
Andy
Carolyn
Hannah
Isabella
Jordan
Katherine
Megan
Nathan
Carol
Caspian
Aurora
Ronan
Freya
Taylor
Iris
Phoenix
Grant
Mira
Selena
Marcus
Greg
Thea
Anthony
Angela
Celeste
Josh
Oberon

Consonants

Unicode	Decimal	IPA	X-SAMPA	Viseme	Example
U+0062	98	b	b	DIS_1	bee
U+0074 U+0283	116 643	tʃ	tS	DIS_8	each
U+0064	100	d	d	DIS_7	dye
U+027E	638	ɾ	4	DIS_7	butter
U+00F0	240	ð	D	DIS_5	then
U+0066	102	f	f	DIS_4	fan
U+0261	609	ɡ	g	DIS_9	guy
U+0068	104	h	h	DIS_9	hat
U+0064 U+0292	100 658	dʒ	dZ	DIS_8	edge
U+006B	107	k	k	DIS_9	sky
U+006B U+02B0	107 688	kʰ	k_h	DIS_9	key
U+006C	108	l	l	DIS_6	lay
U+006D	109	m	m	DIS_1	me
U+006E	110	n	n	DIS_7	knee
U+014B	331	ŋ	N	DIS_9	song
U+0070	112	p	p	DIS_1	speak
U+0070 U+02B0	112 688	pʰ	p_h	DIS_1	pea
U+0279	633	ɹ	r\	DIS_3	ray
U+0073	115	s	s	DIS_7	sea
U+0283	643	ʃ	S	DIS_8	she
U+0074	116	t	t	DIS_7	strip
U+0074 U+02B0	116 688	tʰ	t_h	DIS_7	tea
U+03B8	952	θ	T	DIS_5	thin
U+0076	118	v	v	DIS_4	van
U+0077	119	w	w	DIS_2	way
U+006A	106	j	j	DIS_10	yes
U+007A	122	z	z	DIS_7	zoom
U+0292	658	ʒ	Z	DIS_8	beige

Vowels

Unicode	Decimal	IPA	X-SAMPA	Viseme	Example
U+0251	593	ɑ	A	DIS_13	balm
U+00E6	230	æ	{	DIS_9	trap
U+028C	652	ʌ	V	DIS_13	strut
U+0254 U+0259	596 601	ɔə	O@	DIS_13	caught
U+0061 U+028A	97 650	aʊ	aU	DIS_9	mouth
U+0259	601	ə	@	DIS_9	the
U+0061 U+026A	97 618	aɪ	aI	DIS_9	rice
U+025B	603	ɛ	E	DIS_11	dress
U+0259 U+02DE	601 734	ə˞	@`	DIS_7	butter
U+0065 U+026A	101 618	eɪ	eI	DIS_11	face
U+026A	618	ɪ	I	DIS_10	hit
U+0069 U+02D0	105 720	iː	i:	DIS_10	fleece
U+006F U+028A	111 650	oʊ	oU	DIS_12	goat
U+0254 U+026A	596 618	ɔɪ	OI	DIS_12	choice
U+028A	650	ʊ	U	DIS_11	foot
U+0075 U+02D0	117 720	uː	u:	DIS_3	loose

British English (England) — en-GB

These phonemes apply to the following British English (England) Neural TTS voices:

Amy
Claire
Ben
Jack
Jess
Lauren
Lily
Giles
Sarah
Sue
William

Consonants

Unicode	Decimal	IPA	X-SAMPA	Viseme	Example
U+0062	98	b	b	DIS_1	bee
U+0074 U+0283	116 643	tʃ	tS	DIS_8	each
U+0064	100	d	d	DIS_7	dye
U+00F0	240	ð	D	DIS_5	then
U+0066	102	f	f	DIS_4	fan
U+0261	609	ɡ	g	DIS_9	guy
U+0068	104	h	h	DIS_9	hat
U+0064 U+0292	100 658	dʒ	dZ	DIS_8	edge
U+006B	107	k	k	DIS_9	sky
U+006B U+02B0	107 688	kʰ	k_h	DIS_9	key
U+006C	108	l	l	DIS_6	lay
U+006D	109	m	m	DIS_1	me
U+006E	110	n	n	DIS_7	knee
U+014B	331	ŋ	N	DIS_9	song
U+0070	112	p	p	DIS_1	speak
U+0070 U+02B0	112 688	pʰ	p_h	DIS_1	pea
U+0279	633	ɹ	r\	DIS_3	ray
U+0073	115	s	s	DIS_7	sea
U+0283	643	ʃ	S	DIS_8	she
U+0074	116	t	t	DIS_7	best
U+0074 U+02B0	116 688	tʰ	t_h	DIS_7	tea
U+03B8	952	θ	T	DIS_5	thin
U+0076	118	v	v	DIS_4	van
U+0077	119	w	w	DIS_2	way
U+006A	106	j	j	DIS_10	yes
U+007A	122	z	z	DIS_7	zoom
U+0292	658	ʒ	Z	DIS_8	beige
U+0279	633	ɹ	r\	DIS_3	for
U+007A	122	z	z	DIS_7	cats

Vowels

Unicode	Decimal	IPA	X-SAMPA	Viseme	Example
U+0259	601	ə	@	DIS_9	the
U+025C U+02D0	604 720	ɜː	3:	DIS_9	nurse
U+0061	97	a	a	DIS_13	trap
U+0251 U+02D0	593 720	ɑː	A:	DIS_9	palm
U+0061 U+026A	97 618	aɪ	aI	DIS_9	price
U+0061 U+028A	97 650	aʊ	aU	DIS_9	mouth
U+025B	603	ɛ	E	DIS_11	dress
U+025B U+0259	603 601	ɛə	E@	DIS_11	square
U+0065 U+026A	101 618	eɪ	eI	DIS_11	face
U+026A	618	ɪ	I	DIS_10	kit
U+026A U+0259	618 601	ɪə	I@	DIS_10	near
U+0069 U+02D0	105 720	iː	i:	DIS_10	fleece
U+0252	594	ɒ	Q	DIS_13	lot
U+0254 U+026A	596 618	ɔɪ	OI	DIS_12	choice
U+0254 U+02D0	596 720	ɔː	O:	DIS_13	thought
U+0259 U+028A	601 650	əʊ	@U	DIS_9	goat
U+028A	650	ʊ	U	DIS_11	foot
U+028A U+0259	650 601	ʊə	U@	DIS_11	cure
U+028C	652	ʌ	V	DIS_13	strut
U+0075 U+02D0	117 720	uː	u:	DIS_3	goose

British English (Scotland) — en-GB

These phonemes apply to the following British English (Scotland) Neural TTS voices:

Kirsty
Mairi
Heather
Stuart
Andrew

Consonants

Unicode	Decimal	IPA	X-SAMPA	Viseme	Example
U+0062	98	b	b	DIS_1	bee
U+0074 U+0283	116 643	tʃ	tS	DIS_8	each
U+0064	100	d	d	DIS_7	dye
U+00F0	240	ð	D	DIS_5	then
U+027E	638	ɾ	4	DIS_7	very
U+0066	102	f	f	DIS_4	fan
U+0261	609	ɡ	g	DIS_9	guy
U+0068	104	h	h	DIS_9	hat
U+028D	653	ʍ	W	DIS_2	which
U+0064 U+0292	100 658	dʒ	dZ	DIS_8	edge
U+006B	107	k	k	DIS_9	sky
U+006B U+02B0	107 688	kʰ	k_h	DIS_9	key
U+006C	108	l	l	DIS_6	lay
U+006D	109	m	m	DIS_1	me
U+006E	110	n	n	DIS_7	knee
U+014B	331	ŋ	N	DIS_9	song
U+0070	112	p	p	DIS_1	speak
U+0070 U+02B0	112 688	pʰ	p_h	DIS_1	pea
U+0279	633	ɹ	r\	DIS_3	ray
U+0073	115	s	s	DIS_7	sea
U+0283	643	ʃ	S	DIS_8	she
U+0074	116	t	t	DIS_7	best
U+0074 U+02B0	116 688	tʰ	t_h	DIS_7	tea
U+03B8	952	θ	T	DIS_5	thin
U+0076	118	v	v	DIS_4	van
U+0077	119	w	w	DIS_2	way
U+0078	120	x	x	DIS_9	loch
U+006A	106	j	j	DIS_10	yes
U+007A	122	z	z	DIS_7	zoom
U+0292	658	ʒ	Z	DIS_8	beige
U+007A	122	z	z	DIS_7	cats

Vowels

Unicode	Decimal	IPA	X-SAMPA	Viseme	Example
U+0259	601	ə	@	DIS_9	the
U+0061	97	a	a	DIS_13	trap
U+0251	593	ɑ	A	DIS_13	park
U+0061 U+026A	97 618	aɪ	aI	DIS_9	price
U+028C U+0289	652 649	ʌʉ	V}	DIS_9	mouth
U+025B	603	ɛ	E	DIS_11	dress
U+0065 U+026A	101 618	eɪ	eI	DIS_11	face
U+026A	618	ɪ	I	DIS_10	kit
U+0069	105	i	i	DIS_10	fleece
U+0254	596	ɔ	O	DIS_13	lot
U+0254 U+026A	596 618	ɔɪ	OI	DIS_12	choice
U+006F U+02D0	111 720	oː	o:	DIS_13	goat
U+0289	649	ʉ	}	DIS_11	foot
U+028C	652	ʌ	V	DIS_13	strut
U+0075	117	u	u	DIS_3	goose

British English (Wales) — en-GB

These phonemes apply to the following British English (Wales) Neural TTS voices:

Seren
Tomos
Owain
Rhian
Rhodri
Catrin
Ffion
Gethin

Consonants

Unicode	Decimal	IPA	X-SAMPA	Viseme	Example
U+0062	98	b	b	DIS_1	bee
U+0074 U+0283	116 643	tʃ	tS	DIS_8	each
U+0064	100	d	d	DIS_7	dye
U+027E	638	ɾ	4	DIS_7	ray
U+00F0	240	ð	D	DIS_5	then
U+0066	102	f	f	DIS_4	fan
U+0261	609	ɡ	g	DIS_9	guy
U+0068	104	h	h	DIS_9	hat
U+0064 U+0292	100 658	dʒ	dZ	DIS_8	edge
U+006B	107	k	k	DIS_9	sky
U+006B U+02B0	107 688	kʰ	k_h	DIS_9	k_iy
U+006C	108	l	l	DIS_6	lay
U+026C	620	ɬ	K	DIS_6	llanelli
U+006D	109	m	m	DIS_1	me
U+006E	110	n	n	DIS_7	knee
U+014B	331	ŋ	N	DIS_9	song
U+0070	112	p	p	DIS_1	speak
U+0070 U+02B0	112 688	pʰ	p_h	DIS_1	pea
U+0279	633	ɹ	r\	DIS_3	ray
U+0072	114	r	r	DIS_3	ray
U+0279 U+0325	633 805	ɹ̥	r\_0	DIS_3	rhyl
U+0073	115	s	s	DIS_7	sea
U+0283	643	ʃ	S	DIS_8	she
U+0074	116	t	t	DIS_7	best
U+0074 U+02B0	116 688	tʰ	t_h	DIS_7	tea
U+03B8	952	θ	T	DIS_5	thin
U+0076	118	v	v	DIS_4	van
U+0077	119	w	w	DIS_2	way
U+03C7	967	χ	X	DIS_9	coch
U+006A	106	j	j	DIS_10	yes
U+007A	122	z	z	DIS_7	zoom
U+0292	658	ʒ	Z	DIS_8	beige
U+0279	633	ɹ	r\	DIS_3	for
U+007A	122	z	z	DIS_7	cats

Vowels

Unicode	Decimal	IPA	X-SAMPA	Viseme	Example
U+0259	601	ə	@	DIS_9	the
U+025C U+02D0	604 720	ɜː	3:	DIS_9	nurse
U+0061	97	a	a	DIS_13	trap
U+0251 U+02D0	593 720	ɑː	A:	DIS_9	palm
U+0061 U+026A	97 618	aɪ	aI	DIS_9	price
U+0061 U+028A	97 650	aʊ	aU	DIS_9	mouth
U+025B	603	ɛ	E	DIS_11	dress
U+025B U+0259	603 601	ɛə	E@	DIS_11	square
U+0065 U+026A	101 618	eɪ	eI	DIS_11	face
U+026A	618	ɪ	I	DIS_10	kit
U+026A U+0259	618 601	ɪə	I@	DIS_10	near
U+0069 U+02D0	105 720	iː	i:	DIS_10	fleece
U+0252	594	ɒ	Q	DIS_13	lot
U+0254 U+026A	596 618	ɔɪ	OI	DIS_12	choice
U+0254 U+02D0	596 720	ɔː	O:	DIS_13	thought
U+0259 U+028A	601 650	əʊ	@U	DIS_9	goat
U+028A	650	ʊ	U	DIS_11	foot
U+028A U+0259	650 601	ʊə	U@	DIS_11	cure
U+028C	604	ʌ	V	DIS_13	strut
U+0075 U+02D0	117 720	uː	u:	DIS_3	goose

English (Ireland) — en-IE

These phonemes apply to the following English (Ireland) Neural TTS voice:

Caitlin

Consonants

Unicode	Decimal	IPA	X-SAMPA	Viseme	Example
U+0062	98	b	b	DIS_1	bee
U+0074 U+0283	116 643	tʃ	tS	DIS_8	each
U+0064	100	d	d	DIS_7	dye
U+00F0	240	ð	D	DIS_5	then
U+0066	102	f	f	DIS_4	fan
U+0261	609	ɡ	g	DIS_9	guy
U+0068	104	h	h	DIS_9	hat
U+028D	653	ʍ	W	DIS_2	which
U+0064 U+0292	100 658	dʒ	dZ	DIS_8	edge
U+006B	107	k	k	DIS_9	sky
U+006B U+02B0	107 688	kʰ	k_h	DIS_9	k_iy
U+006C	108	l	l	DIS_6	lay
U+006D	109	m	m	DIS_1	me
U+006E	110	n	n	DIS_7	knee
U+014B	331	ŋ	N	DIS_9	song
U+0070	112	p	p	DIS_1	speak
U+0070 U+02B0	112 688	pʰ	p_h	DIS_1	pea
U+0279	633	ɹ	r\	DIS_3	ray
U+0073	115	s	s	DIS_7	sea
U+0283	643	ʃ	S	DIS_8	she
U+0074	116	t	t	DIS_7	best
U+0074 U+02B0	116 688	tʰ	t_h	DIS_7	tea
U+03B8	952	θ	T	DIS_5	thin
U+0074 U+0320	116 800	t̠	t_-	DIS_7	cat
U+0076	118	v	v	DIS_4	van
U+0077	119	w	w	DIS_2	way
U+006A	106	j	j	DIS_10	yes
U+007A	122	z	z	DIS_7	zoom
U+0292	658	ʒ	Z	DIS_8	beige
U+0279	633	ɹ	r\	DIS_3	for
U+007A	122	z	z	DIS_7	cats
U+0074 U+0320	116 800	t̠	t_-	DIS_7	hat

Vowels

Unicode	Decimal	IPA	X-SAMPA	Viseme	Example
U+0259	601	ə	@	DIS_9	the
U+025C U+02D0	604 720	ɜː	3:	DIS_9	nurse
U+0061	97	a	a	DIS_13	trap
U+0061 U+02D0	97 720	aː	a:	DIS_13	palm
U+0061 U+026A	97 618	aɪ	aI	DIS_9	price
U+025C U+028A	604 650	ɜʊ	3U	DIS_9	mouth
U+025B	603	ɛ	E	DIS_11	dress
U+025B U+026A	603 618	ɛɪ	EI	DIS_11	face
U+025B U+0259	603 601	ɛə	E@	DIS_11	square
U+026A	618	ɪ	I	DIS_10	kit
U+0069 U+02D0	105 720	iː	i:	DIS_10	fleece
U+026A U+0259	618 601	ɪə	I@	DIS_10	near
U+0252	594	ɒ	Q	DIS_13	lot
U+0254 U+026A	596 618	ɔɪ	OI	DIS_12	choice
U+0252 U+02D0	594 720	ɒː	Q:	DIS_13	thought
U+006F U+028A	111 650	oʊ	oU	DIS_12	goat
U+028A	650	ʊ	U	DIS_11	foot
U+0075 U+02D0	117 720	uː	u:	DIS_3	goose
U+028A U+0259	650 601	ʊə	U@	DIS_11	cure

Viseme values use the standard Capacity viseme set (for lip-sync and avatar animation). X-SAMPA is the ASCII-encoded equivalent of the IPA symbol.

Was this article helpful?