Japanese Phonemes

The tables below list the full set of phonemes supported by Capacity Private Cloud Neural and LLM TTS for Japanese (ja-JP). 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.

These phonemes apply to the following Japanese Neural TTS voices:

Yuki
Akari

Consonants

Unicode	Decimal	IPA	X-SAMPA	Viseme	Example
U+0274	628	ɴ	N\	DIS_7	ほん
U+0070	112	p	p	DIS_1	ぱん
U+0074	116	t	t	DIS_7	たこ
U+006B	107	k	k	DIS_9	かご
U+0278	632	ɸ	p\	DIS_4	ふろ
U+0073	115	s	s	DIS_7	さけ
U+0255	597	ɕ	s\	DIS_8	あし
U+0068	104	h	h	DIS_9	は
U+02A6	678	ʦ	ts	DIS_7	まつ
U+02A8	680	ʨ	ts\	DIS_8	おちゃ
U+0062	98	b	b	DIS_1	ばす
U+0064	100	d	d	DIS_7	はだ
U+0067	103	g	g	DIS_9	けが
U+007A	122	z	z	DIS_7	かぜ
U+0291	657	ʑ	z\	DIS_8	かじ
U+006D	109	m	m	DIS_1	まど
U+006E	110	n	n	DIS_7	かね
U+027D	637	ɽ	r`	DIS_3	からい
U+0270	624	ɰ	M\	DIS_9	わらび
U+0294	660	ʔ	?	k	やけっ

Vowels

Unicode	Decimal	IPA	X-SAMPA	Viseme	Example
U+0061	97	a	a	DIS_13	あす
U+0065	101	e	e	DIS_11	て
U+0069	105	i	i	DIS_10	いす
U+006F	111	o	o	DIS_12	おと
U+026F	623	ɯ	M	DIS_3	うみ
U+02B2 U+0061	690 97	ʲa	_ja	DIS_10	きゃく
U+02B2 U+0065	690 101	ʲe	_je	DIS_13	いぇっと
U+02B2 U+006F	690 111	ʲo	_jo	DIS_13	きょーと
U+02B2 U+026F	690 623	ʲɯ	_jM	DIS_3	にゅーす
U+0069 U+0325	105 805	i̥	i_0	DIS_10	きた
U+026F U+0325	623 805	ɯ̥	M_0	DIS_3	くし
U+0000	0			DIS_0	う

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?