Services or capabilities described in Amazon Web Services documentation might vary by Region. To see the differences applicable to the China Regions, see Getting Started with Amazon Web Services in China (PDF).

Character sets for custom vocabularies and vocabulary filters

For each language Amazon Transcribe supports, there is a specific set of characters Amazon Transcribe can recognize. When you create a custom vocabulary or vocabulary filter, use only the characters listed in your language's character set. If you use unsupported characters, your custom vocabulary or vocabulary filter fails.

Many Unicode characters can appear identical in popular fonts, even if they use different code points. Only the code points listed in this guide are supported. For example, the French word déjà can be rendered using precomposed characters (where one Unicode value represents an accented character) or decomposed characters (where two Unicode values represent an accented character, one value for the base character and another for the accent).

Abkhaz character set

For Abkhaz custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Afrikaans character set

For Afrikaans custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Arabic character set

For Arabic custom vocabularies, you can use the following Unicode characters in the Phrase field. You can also use the hyphen (-) character to separate words.

Asturian character set

For Asturian custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Azerbaijani character set

For Azerbaijani custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Armenian character set

For Armenian custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Bashkir character set

For Bashkir custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Basque character set

For Basque custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Belarusian character set

For Belarusian custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Bengali character set

For Bengali custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Bosnian character set

For Bosnian custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Bulgarian character set

For Bulgarian custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Catalan character set

For Catalan custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Central Kurdish character set

For Central Kurdish custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Chinese, Mandarin (Simplified) character set

For Chinese (Simplified) custom vocabularies, the Phrase field can use any of the characters listed in the following file:

The SoundsLike field can contain the pinyin syllables listed in the following file:

When you use pinyin syllables in the SoundsLike field, separate the syllables with a hyphen (-).

Amazon Transcribe represents the four tones in Chinese (Simplified) using numbers. The following table shows how tone marks are mapped for the word 'ma'.

Chinese (Simplified) custom vocabularies don't use the IPA field, but you must still include the IPA header in the custom vocabulary table.

The following example is an input file in text format. The example uses spaces to align the columns. Your input files should use TAB characters to separate the columns. Include spaces only in the DisplayAs column.

Phrase       SoundsLike               IPA     DisplayAs
康健          kang1-jian4 
谴责          qian3-ze2 
国防大臣        guo2-fang2-da4-chen2 
世界博览会      shi4-jie4-bo2-lan3-hui4          世博会

Chinese, Mandarin (Traditional) character set

For Chinese (Traditional) custom vocabularies, the Phrase field can use any of the characters listed in the following file:

The SoundsLike field can contain the zhuyin syllables listed in the following file:

When you use zhuyin syllables in the SoundsLike field, separate the syllables with a hyphen (-).

Amazon Transcribe represents the four tones in Chinese (Traditional) using numbers. The following table shows how tone marks are mapped for the word ㄇㄚ.

Chinese (Traditional) custom vocabularies don't use the IPA field, but you must still include the IPA header in the custom vocabulary table.

The following example is an input file in text format. The example uses spaces to align the columns. Your input files should use TAB characters to separate the columns. Include spaces only in the DisplayAs column.

Phrase        SoundsLike                     IPA        DisplayAs
健康          ㄐㄧㄢˋ-ㄎㄤ 
譴責          ㄑㄧㄢˇ-ㄗㄜˊ 
國防部長       ㄍㄨㄛˊ-ㄈㄤˊ-ㄅㄨˋ-ㄓㄤˇ 
世界博覽會     ㄕˋ-ㄐㄧㄝˋ-ㄅㄛˊ-ㄌㄢˇ-ㄏㄨㄟˋ             世博會

Chinese, Cantonese (Hong Kong), Traditional character set

For Chinese (Cantonese) Hong Kong custom vocabularies, the Phrase field can use any of the characters listed in the following file:

Croatian character set

For Croatian custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Czech character set

For Czech custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Danish character set

For Danish custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Dutch character set

For Dutch custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

English character set

For English custom vocabularies, you can use the following characters in the Phrase field:

Estonian character set

For Estonian custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Farsi character set

For Farsi custom vocabularies, you can use the following characters in the Phrase field.

Finnish character set

For Finnish custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

French character set

For French custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Galician character set

For Galician custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Georgian character set

For Georgian custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

German character set

For German custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Greek character set

For Greek custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Gujarati character set

For Gujarati custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Hausa character set

For Hausa custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Hebrew character set

For Hebrew custom vocabularies, you can use the following Unicode characters in the Phrase field:

Hindi character set

For Hindi custom vocabularies, you can use the following Unicode characters in the Phrase field:

Amazon Transcribe maps the following characters:

Hungarian character set

For Hungarian custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Icelandic character set

For Icelandic custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Indonesian character set

For Indonesian custom vocabularies, you can use the following characters in the Phrase field:

Italian character set

For Italian custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Japanese character set

For Japanese custom vocabularies, the DisplayAs field supports all hiragana, katakana, and kanji characters, and fullwidth romaji capital letters.

The Phrase field supports the characters listed in the following file:

Kabyle character set

For Kabyle custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Kannada character set

For Kannada custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Kazakh character set

For Kazakh custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Kinyarwanda character set

For Kinyarwanda custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Korean character set

For Korean custom vocabularies, you can use any of the Hangul syllables in the Phrase field. For more information, see Hangul Syllables on Wikipedia.

Kyrgyz character set

For Kyrgyz custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Latvian character set

For Latvian custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Lithuanian character set

For Lithuanian custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Luganda character set

For Luganda custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Macedonian character set

For Macedonian custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Malay character set

For Malay custom vocabularies, you can use the following characters in the Phrase field:

Malayalam character set

For Malayalam custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Maltese character set

For Maltese custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Marathi character set

For Marathi custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Meadow Mari character set

For Meadow Mari custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Mongolian character set

For Mongolian custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Norwegian Bokmål character set

For Norwegian Bokmål custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Odia/Oriya character set

For Odia/Oriya custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Pashto character set

For Pashto custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Polish character set

For Polish custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Portuguese character set

For Portuguese custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Punjabi character set

For Punjabi custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Romanian character set

For Romanian custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Russian character set

For Russian custom vocabularies, you can use the following characters in the Phrase field:

Serbian character set

For Serbian custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Sinhala character set

For Sinhala custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Slovak character set

For Slovak custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Slovenian character set

For Slovenian custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Somali character set

For Somali custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Spanish character set

For Spanish custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Sundanese character set

For Sundanese custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Swahili character set

For Swahili custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Swedish character set

For Swedish custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Tagalog/Filipino character set

For Tagalog/Filipino custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Tamil character set

For Tamil custom vocabularies, you can use the following characters in the Phrase field:

Tatar character set

For Tatar custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Telugu character set

For Telugu custom vocabularies, you can use the following characters in the Phrase field:

Thai character set

For Thai custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Turkish character set

For Turkish custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Ukrainian character set

For Ukrainian custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Uyghur character set

For Uyghur custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Uzbek character set

For Uzbek custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Vietnamese character set

Amazon Transcribe represents the six tones in Vietnamese using numbers. The following table shows how tone marks are mapped for the word 'ma'.

For Vietnamese custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Welsh character set

For Welsh custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Wolof character set

For Wolof custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field:

Zulu character set

For Zulu custom vocabularies, you can use the following characters in the Phrase field:

You can also use the following Unicode characters in the Phrase field: