German Phonemes

The tables below list the full set of phonemes supported by Capacity Private Cloud Neural and LLM TTS for German. 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 for each locale.

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.

German (Germany) — de-DE

These phonemes apply to the following German (Germany) Neural TTS voices:

  • Alex
  • Gudrun

Supplementary English phonemes. In addition to the native German (Germany) inventory, this phoneme set includes a number of English phonemes (marked with * and grouped at the end of each table). These are provided so that English words and loanwords that appear within German (Germany) text are pronounced correctly.

Consonants

UnicodeDecimalIPAX-SAMPAVisemeExample
U+0070112ppDIS_1Prinz
U+006298bbDIS_1Abend
U+0074116ttDIS_7Hütte
U+0064100ddDIS_7jeder
U+0261609ɡgDIS_9Auge
U+006B107kkDIS_9Kunst
U+0066102ffDIS_4Affe
U+0076118vvDIS_4warum
U+0073115ssDIS_7Tasse
U+007A122zzDIS_7Hase
U+0292658ʒZDIS_8Genie
U+0283643ʃSDIS_8Schiff
U+0064 U+0292100 658dZDIS_8Djungle
U+0074 U+0283116 643tSDIS_8deutsch
U+006D109mmDIS_1mein
U+006E110nnDIS_7nein
U+014B331ŋNDIS_9Ding
U+006C108llDIS_6bald
U+006A106jjDIS_10Jahr
U+0281641ʁRDIS_3Rat
U+0262 U+0306610 774ɢ̆G\_XDIS_3Herde
U+0068104hhDIS_9Hafen
U+00E7231çCDIS_9sicher
U+0078120xxDIS_9Buch
U+02A6678ʦtsDIS_7Zahl
U+0070 U+032A U+0066112 810 102p̪fp_dfDIS_1Pfund
U+0294660ʔ?kAst
U+03B8952θTDIS_5think *
U+00F0240ðDDIS_5that *
U+0077119wwDIS_2water *
U+0279633ɹr\DIS_3traffic *

Vowels

UnicodeDecimalIPAX-SAMPAVisemeExample
U+0259601ə@DIS_9machen
U+0061 U+030897 776a_"DIS_13Anfang
U+0061 U+0308 U+02D097 776 720äːa_":DIS_13Zahn
U+025B603ɛEDIS_11hätte
U+025B U+02D0603 720ɛːE:DIS_11spät
U+025B U+0306603 774ɛ̆E_XDIS_11Pedal
U+0065101eeDIS_11Leder
U+026A618ɪIDIS_10still
U+0069105iiDIS_10Niere
U+0254596ɔODIS_13Motte
U+006F111ooDIS_12Dose
U+0254 U+026A596 618ɔɪOIDIS_12Leute
U+0153339œ9DIS_12könnte
U+00F8248ø2DIS_3schön
U+028A650ʊUDIS_11bunt
U+0075117uuDIS_3Mut
U+028F655ʏYDIS_3hübsch
U+0079 U+02D0121 720y:DIS_3rügen
U+0250592ɐ6DIS_9Vater
U+025B U+0303603 771ɛ̃E~DIS_11Teint
U+0251 U+0303593 771ɑ̃A~DIS_13Chance
U+0254 U+0303596 771ɔ̃O~DIS_13Pardon
U+0079 U+0303121 771y~DIS_13Parfum
U+0061 U+026A97 618aIDIS_9weiß
U+0061 U+028A97 650aUDIS_9Auto
U+025B U+026A603 618ɛɪEIDIS_11Steak

* Supplementary English phoneme — included so that English words and loanwords embedded in German (Germany) text render with correct pronunciation.

German (Austria) — de-AT

These phonemes apply to the following German (Austria) Neural TTS voice:

  • Leopold

Consonants

UnicodeDecimalIPAX-SAMPAVisemeExample
U+0070112ppDIS_1Prinz
U+006298bbDIS_1Abend
U+0074116ttDIS_7Hütte
U+0064100ddDIS_7jeder
U+0261609ɡgDIS_9Auge
U+006B107kkDIS_9Kunst
U+0066102ffDIS_4Affe
U+0076118vvDIS_4Wasser
U+0073115ssDIS_7Tasse
U+007A122zzDIS_7Hase
U+0292658ʒZDIS_8Genie
U+0283643ʃSDIS_8Schiff
U+006D109mmDIS_1mein
U+006E110nnDIS_7nein
U+014B331ŋNDIS_9Ding
U+006C108llDIS_6bald
U+006A106jjDIS_10Jahr
U+0281641ʁRDIS_3Rat
U+0068104hhDIS_9Hafen
U+00E7231çCDIS_9sicher
U+0078120xxDIS_9Buch

Vowels

UnicodeDecimalIPAX-SAMPAVisemeExample
U+0259601ə@DIS_9machen
U+0061 U+030897 776a_"DIS_13Anfang
U+0061 U+0308 U+02D097 776 720äːa_":DIS_13Zahn
U+025B U+0306603 774ɛ̆E_XDIS_11nett
U+0065101eeDIS_11Leder
U+026A618ɪIDIS_10still
U+0069105iiDIS_10Niere
U+0254596ɔODIS_13Motte
U+006F111ooDIS_12Dose
U+0254 U+026A596 618ɔɪOIDIS_12Leute
U+0153339œ9DIS_12könnte
U+00F8248ø2DIS_3schön
U+028A650ʊUDIS_11bunt
U+0075117uuDIS_3Mut
U+028F655ʏYDIS_3Hütte
U+0079 U+02D0121 720y:DIS_3rügen
U+0250592ɐ6DIS_9Vater
U+025B U+0303603 771ɛ̃E~DIS_11Teint
U+0251 U+0303593 771ɑ̃A~DIS_13Chance
U+0254 U+0303596 771ɔ̃O~DIS_13Bronze
U+0079 U+0303121 771y~DIS_13Parfum
U+0061 U+026A97 618aIDIS_9weiß
U+0061 U+028A97 650aUDIS_9Auto

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?