- Specify the speech recognizer language
- Identify the default language
- Confirm an installed language
- Specify a language
- Remarks
- Определение языка для распознавателя речи Specify the speech recognizer language
- Определение языка, используемого по умолчанию Identify the default language
- Подтверждение установленного языка Confirm an installed language
- Определение языка Specify a language
- Комментарии Remarks
- Связанные статьи Related articles
- Speech recognition is not supported in the current language
- Language and voice support for the Speech service
- Speech-to-text
- Text-to-speech
- Neural voices
- Neural voices in preview
- Standard voices
- Customization
- Speech translation
- Text languages
- Speaker Recognition
Specify the speech recognizer language
Learn how to select an installed language to use for speech recognition.
Here, we enumerate the languages installed on a system, identify which is the default language, and select a different language for recognition.
Prerequisites:
You should have a basic understanding of speech recognition and recognition constraints.
If you’re new to developing Windows apps, have a look through these topics to get familiar with the technologies discussed here.
User experience guidelines:
For helpful tips about designing a useful and engaging speech-enabled app, see Speech design guidelines .
Identify the default language
A speech recognizer uses the system speech language as its default recognition language. This language is set by the user on the device Settings > System > Speech > Speech Language screen.
We identify the default language by checking the SystemSpeechLanguage static property.
Confirm an installed language
Installed languages can vary between devices. You should verify the existence of a language if you depend on it for a particular constraint.
NoteВ В A reboot is required after a new language pack is installed. An exception with error code SPERR_NOT_FOUND (0x8004503a) is raised if the specified language is not supported or has not finished installing.
Determine the supported languages on a device by checking one of two static properties of the SpeechRecognizer class:
SupportedTopicLanguages—The collection of Language objects used with predefined dictation and web search grammars.
SupportedGrammarLanguages—The collection of Language objects used with a list constraint or a Speech Recognition Grammar Specification (SRGS) file.
Specify a language
To specify a language, pass a Language object in the SpeechRecognizer constructor.
Here, we specify «en-US» as the recognition language.
Remarks
A topic constraint can be configured by adding a SpeechRecognitionTopicConstraint to the Constraints collection of the SpeechRecognizer and then calling CompileConstraintsAsync. A SpeechRecognitionResultStatus of TopicLanguageNotSupported is returned if the recognizer is not initialized with a supported topic language.
A list constraint is configured by adding a SpeechRecognitionListConstraint to the Constraints collection of the SpeechRecognizer and then calling CompileConstraintsAsync. You cannot specify the language of a custom list directly. Instead, the list will be processed using the language of the recognizer.
An SRGS grammar is an open-standard XML format represented by the SpeechRecognitionGrammarFileConstraint class. Unlike custom lists, you can specify the language of the grammar in the SRGS markup. CompileConstraintsAsync fails with a SpeechRecognitionResultStatus of TopicLanguageNotSupported if the recognizer is not initialized to the same language as the SRGS markup.
Определение языка для распознавателя речи Specify the speech recognizer language
Узнайте, как выбрать установленный язык для распознавания речи. Learn how to select an installed language to use for speech recognition.
Здесь мы перечисляем языки, установленные в системе, определяем язык, используемый по умолчанию, и выбираем другой язык для распознавания. Here, we enumerate the languages installed on a system, identify which is the default language, and select a different language for recognition.
Предварительные условия. Prerequisites:
В данной статье используются материалы статьи Распознавание речи. This topic builds on Speech recognition.
От вас требуется понимание основных принципов распознавания речи и знание соответствующих ограничений. You should have a basic understanding of speech recognition and recognition constraints.
Если вы еще не знакомы с разработкой приложений для Windows, ознакомьтесь с этими разделами, чтобы ознакомиться с технологиями, обсуждаемыми здесь. If you’re new to developing Windows apps, have a look through these topics to get familiar with the technologies discussed here.
Рекомендации по работе с пользователем: User experience guidelines:
Полезные советы по разработке практичного и привлекательного приложения с поддержкой голосовых функций см. в разделе Рекомендации по проектированию голосовых функций. For helpful tips about designing a useful and engaging speech-enabled app, see Speech design guidelines .
Определение языка, используемого по умолчанию Identify the default language
В качестве языка по умолчанию распознаватель речи использует язык для голосовых функций, установленный в системе. A speech recognizer uses the system speech language as its default recognition language. Этот язык устанавливает пользователь на устройстве, в разделе «Параметры» > «Система» > «Речь» > «Язык голосовых функций». This language is set by the user on the device Settings > System > Speech > Speech Language screen.
Чтобы определить язык по умолчанию, нужно проверить статическое свойство SystemSpeechLanguage. We identify the default language by checking the SystemSpeechLanguage static property.
Подтверждение установленного языка Confirm an installed language
На разных устройствах установленные языки могут отличаться. Installed languages can vary between devices. Следует проверить наличие языка, если с ним связано какое-либо ограничение, которое имеет для вас значение. You should verify the existence of a language if you depend on it for a particular constraint.
Примечание. После установки нового языкового пакета требуется перезагрузка. Note A reboot is required after a new language pack is installed. Исключение с кодом ошибки СПЕРР _ не _ найдено (0x8004503a) возникает, если указанный язык не поддерживается или не завершил установку. An exception with error code SPERR_NOT_FOUND (0x8004503a) is raised if the specified language is not supported or has not finished installing.
Определите поддерживаемые языки на устройстве, проверив одно из двух статических свойств класса SpeechRecognizer: Determine the supported languages on a device by checking one of two static properties of the SpeechRecognizer class:
SupportedTopicLanguages — коллекция объектов Language, используемых с предустановленными правилами грамматики для диктовки и поиска в Интернете. SupportedTopicLanguages—The collection of Language objects used with predefined dictation and web search grammars.
SupportedGrammarLanguages — коллекция объектов Language, используемых с ограничением по списку или файлом определения грамматики для распознавания речи (SRGS). SupportedGrammarLanguages—The collection of Language objects used with a list constraint or a Speech Recognition Grammar Specification (SRGS) file.
Определение языка Specify a language
Чтобы определить язык, передайте объект Language в конструктор SpeechRecognizer. To specify a language, pass a Language object in the SpeechRecognizer constructor.
Здесь мы определяем en-US как язык для распознавания. Here, we specify «en-US» as the recognition language.
Комментарии Remarks
Ограничение по одной теме можно настроить, добавив SpeechRecognitionTopicConstraint в коллекцию Constraints средства SpeechRecognizer, а затем вызвав CompileConstraintsAsync. A topic constraint can be configured by adding a SpeechRecognitionTopicConstraint to the Constraints collection of the SpeechRecognizer and then calling CompileConstraintsAsync. Если распознаватель не удалось инициализировать с поддерживаемым языком темы, возвращается состояние SpeechRecognitionResultStatus для TopicLanguageNotSupported . A SpeechRecognitionResultStatus of TopicLanguageNotSupported is returned if the recognizer is not initialized with a supported topic language.
Ограничение по списку можно настроить, добавив SpeechRecognitionListConstraint в коллекцию Constraints средства SpeechRecognizer, а затем вызвав CompileConstraintsAsync. A list constraint is configured by adding a SpeechRecognitionListConstraint to the Constraints collection of the SpeechRecognizer and then calling CompileConstraintsAsync. Вы не можете задать язык пользовательского списка напрямую. You cannot specify the language of a custom list directly. Список будет обрабатываться с использованием языка распознавателя. Instead, the list will be processed using the language of the recognizer.
Грамматика SRGS – это открытый формат XML, представляемый классом SpeechRecognitionGrammarFileConstraint. An SRGS grammar is an open-standard XML format represented by the SpeechRecognitionGrammarFileConstraint class. В отличие от пользовательских списков язык грамматики можно указать в разметке SRGS. Unlike custom lists, you can specify the language of the grammar in the SRGS markup. Выполнение CompileConstraintsAsync завершается ошибкой с состоянием SpeechRecognitionResultStatus для TopicLanguageNotSupported , если распознаватель не удалось инициализировать на языке разметки SRGS. CompileConstraintsAsync fails with a SpeechRecognitionResultStatus of TopicLanguageNotSupported if the recognizer is not initialized to the same language as the SRGS markup.
Связанные статьи Related articles
Примеры Samples
Speech recognition is not supported in the current language
Remember — This is a public forum so never post private information such as email or phone numbers!
- Programs you are having problems with speech recognition
- Error messages Speech recognition is not supported in the current language
- Recent changes you made to your computer no
- What you have already tried to fix the problem no
You could try changing the locale to a different one, restart, change it back to your preferred locale and see if this sorts out your problem.
Refer this article for help.
The idea behind that is to just make sure that the locale settings on your system are properly applied as it might have been messed up somewhere either by another program or could be anything else.
Alternatively you could try this step.
1. Open Control Panel then Speech Recognition Options.
2. In the upper right of the Speech Recognition Option window click Advanced Speech Options.
3. Remove the checkmark next to, ‘Allow computer to review your documents’.
4. Click Apply.
If the above does not work, go back to Speech Recognition Options and click Train Profile and see if you are able to Train. Failing that, click the New button and try creating a new User Profile with a new name. If that works, you will be able to delete your first profile.
Hope this helps.
Shinmila H — Microsoft Support
Visit our Microsoft Answers Feedback Forum and let us know what you think.
Language and voice support for the Speech service
Language support varies by Speech service functionality. The following tables summarize language support for Speech-to-text, Text-to-speech, and Speech translation service offerings.
Speech-to-text
Both the Microsoft Speech SDK and the REST API support the following languages (locales).
To improve accuracy, customization is offered for a subset of the languages through uploading Audio + Human-labeled Transcripts or Related Text: Sentences. Support for customization of the acoustic model with Audio + Human-labeled Transcripts is limited to the specific base models listed below. Other base models and languages will only use the text of the transcripts to train custom models just like with Related Text: Sentences. To learn more about customization, see Get started with Custom Speech.
Click on Adaptation Data -> scroll down to section «Pronunciation Datasets» -> Click on Import -> Locale: the list of locales there correspond to the supported locales —>
| Language | Locale (BCP-47) | Customizations | Language detection |
|---|---|---|---|
| Arabic (Bahrain), modern standard | ar-BH | Text | |
| Arabic (Egypt) | ar-EG | Text | Yes |
| Arabic (Iraq) | ar-IQ | Text | |
| Arabic (Israel) | ar-IL | Text | |
| Arabic (Jordan) | ar-JO | Text | |
| Arabic (Kuwait) | ar-KW | Text | |
| Arabic (Lebanon) | ar-LB | Text | |
| Arabic (Oman) | ar-OM | Text | |
| Arabic (Qatar) | ar-QA | Text | |
| Arabic (Saudi Arabia) | ar-SA | Text | |
| Arabic (State of Palestine) | ar-PS | Text | |
| Arabic (Syria) | ar-SY | Text | |
| Arabic (United Arab Emirates) | ar-AE | Text | |
| Bulgarian (Bulgaria) | bg-BG | Text | |
| Catalan (Spain) | ca-ES | Text | Yes |
| Chinese (Cantonese, Traditional) | zh-HK | Audio (20201015) Text | Yes |
| Chinese (Mandarin, Simplified) | zh-CN | Audio (20200910) Text | Yes |
| Chinese (Taiwanese Mandarin) | zh-TW | Audio (20190701, 20201015) Text | Yes |
| Croatian (Croatia) | hr-HR | Text | |
| Czech (Czech Republic) | cs-CZ | Text | |
| Danish (Denmark) | da-DK | Text | Yes |
| Dutch (Netherlands) | nl-NL | Audio (20201015) Text Pronunciation | Yes |
| English (Australia) | en-AU | Audio (20201019) Text | Yes |
| English (Canada) | en-CA | Audio (20201019) Text | Yes |
| English (Ghana) | en-GH | Text | |
| English (Hong Kong) | en-HK | Text | |
| English (India) | en-IN | Audio (20200923) Text | |
| English (Ireland) | en-IE | Text | |
| English (Kenya) | en-KE | Text | |
| English (New Zealand) | en-NZ | Audio (20201019) Text | |
| English (Nigeria) | en-NG | Text | |
| English (Philippines) | en-PH | Text | |
| English (Singapore) | en-SG | Text | |
| English (South Africa) | en-ZA | Text | |
| English (Tanzania) | en-TZ | Text | |
| English (United Kingdom) | en-GB | Audio (20201019) Text Pronunciation | Yes |
| English (United States) | en-US | Audio (20201019) Text Pronunciation | Yes |
| Estonian(Estonia) | et-EE | Text | |
| Filipino (Philippines) | fil-PH | Text | |
| Finnish (Finland) | fi-FI | Text | Yes |
| French (Canada) | fr-CA | Audio (20201015) Text Pronunciation | Yes |
| French (France) | fr-FR | Audio (20201015) Text Pronunciation | Yes |
| French (Switzerland) | fr-CH | Text Pronunciation | |
| German (Austria) | de-AT | Text Pronunciation | |
| German (Germany) | de-DE | Audio (20190701, 20200619, 20201127) Text Pronunciation | Yes |
| Greek (Greece) | el-GR | Text | Yes |
| Gujarati (Indian) | gu-IN | Text | |
| Hindi (India) | hi-IN | Audio (20200701) Text | Yes |
| Hungarian (Hungary) | hu-HU | Text | |
| Indonesian (Indonesia) | id-ID | Text | |
| Irish(Ireland) | ga-IE | Text | |
| Italian (Italy) | it-IT | Audio (20201016) Text Pronunciation | Yes |
| Japanese (Japan) | ja-JP | Text | Yes |
| Korean (Korea) | ko-KR | Audio (20201015) Text | Yes |
| Latvian (Latvia) | lv-LV | Text | |
| Lithuanian (Lithuania) | lt-LT | Text | |
| Malay (Malaysia) | ms-MY | Text | |
| Maltese (Malta) | mt-MT | Text | |
| Marathi (India) | mr-IN | Text | |
| Norwegian (BokmГҐl, Norway) | nb-NO | Text | Yes |
| Polish (Poland) | pl-PL | Text | Yes |
| Portuguese (Brazil) | pt-BR | Audio (20190620, 20201015) Text Pronunciation | Yes |
| Portuguese (Portugal) | pt-PT | Text Pronunciation | Yes |
| Romanian (Romania) | ro-RO | Text | Yes |
| Russian (Russia) | ru-RU | Audio (20200907) Text | Yes |
| Slovak (Slovakia) | sk-SK | Text | |
| Slovenian (Slovenia) | sl-SI | Text | |
| Spanish (Argentina) | es-AR | Text Pronunciation | |
| Spanish (Bolivia) | es-BO | Text Pronunciation | |
| Spanish (Chile) | es-CL | Text Pronunciation | |
| Spanish (Colombia) | es-CO | Text Pronunciation | |
| Spanish (Costa Rica) | es-CR | Text Pronunciation | |
| Spanish (Cuba) | es-CU | Text Pronunciation | |
| Spanish (Dominican Republic) | es-DO | Text Pronunciation | |
| Spanish (Ecuador) | es-EC | Text Pronunciation | |
| Spanish (El Salvador) | es-SV | Text Pronunciation | |
| Spanish (Equatorial Guinea) | es-GQ | Text | |
| Spanish (Guatemala) | es-GT | Text Pronunciation | |
| Spanish (Honduras) | es-HN | Text Pronunciation | |
| Spanish (Mexico) | es-MX | Audio (20200907) Text Pronunciation | Yes |
| Spanish (Nicaragua) | es-NI | Text Pronunciation | |
| Spanish (Panama) | es-PA | Text Pronunciation | |
| Spanish (Paraguay) | es-PY | Text Pronunciation | |
| Spanish (Peru) | es-PE | Text Pronunciation | |
| Spanish (Puerto Rico) | es-PR | Text Pronunciation | |
| Spanish (Spain) | es-ES | Audio (20201015) Text Pronunciation | Yes |
| Spanish (Uruguay) | es-UY | Text Pronunciation | |
| Spanish (USA) | es-US | Text Pronunciation | |
| Spanish (Venezuela) | es-VE | Text Pronunciation | |
| Swedish (Sweden) | sv-SE | Text | Yes |
| Tamil (India) | ta-IN | Text | |
| Telugu (India) | te-IN | Text | |
| Thai (Thailand) | th-TH | Text | Yes |
| Turkish (Turkey) | tr-TR | Text | |
| Vietnamese (Vietnam) | vi-VN | Text |
Text-to-speech
Both the Microsoft Speech SDK and REST APIs support these voices, each of which supports a specific language and dialect, identified by locale. You can also get a full list of languages and voices supported for each specific region/endpoint through the voices/list API.
Pricing varies for standard, custom and neural voices. Please visit the Pricing page for additional information.
Neural voices
Neural text-to-speech is a new type of speech synthesis powered by deep neural networks. When using a neural voice, synthesized speech is nearly indistinguishable from the human recordings.
Neural voices can be used to make interactions with chatbots and voice assistants more natural and engaging, convert digital texts such as e-books into audiobooks and enhance in-car navigation systems. With the human-like natural prosody and clear articulation of words, neural voices significantly reduce listening fatigue when users interact with AI systems.
Neural voices are created from samples that use a 24 khz sample rate. All voices can upsample or downsample to other sample rates when synthesizing.
| Language | Locale | Gender | Voice name | Style support |
|---|---|---|---|---|
| Arabic (Egypt) | ar-EG | Female | ar-EG-SalmaNeural | General |
| Arabic (Egypt) | ar-EG | Male | ar-EG-ShakirNeural | General |
| Arabic (Saudi Arabia) | ar-SA | Female | ar-SA-ZariyahNeural | General |
| Arabic (Saudi Arabia) | ar-SA | Male | ar-SA-HamedNeural | General |
| Bulgarian (Bulgaria) | bg-BG | Female | bg-BG-KalinaNeural | General |
| Bulgarian (Bulgaria) | bg-BG | Male | bg-BG-BorislavNeural | General |
| Catalan (Spain) | ca-ES | Female | ca-ES-AlbaNeural | General |
| Catalan (Spain) | ca-ES | Female | ca-ES-JoanaNeural | General |
| Catalan (Spain) | ca-ES | Male | ca-ES-EnricNeural | General |
| Chinese (Cantonese, Traditional) | zh-HK | Female | zh-HK-HiuGaaiNeural | General |
| Chinese (Cantonese, Traditional) | zh-HK | Female | zh-HK-HiuMaanNeural | General |
| Chinese (Cantonese, Traditional) | zh-HK | Male | zh-HK-WanLungNeural | General |
| Chinese (Mandarin, Simplified) | zh-CN | Female | zh-CN-XiaoxiaoNeural | General, multiple voice styles available using SSML |
| Chinese (Mandarin, Simplified) | zh-CN | Female | zh-CN-XiaoyouNeural | Child voice, optimized for story narrating |
| Chinese (Mandarin, Simplified) | zh-CN | Male | zh-CN-YunyangNeural | Optimized for news reading, multiple voice styles available using SSML |
| Chinese (Mandarin, Simplified) | zh-CN | Male | zh-CN-YunyeNeural | Optimized for story narrating |
| Chinese (Taiwanese Mandarin) | zh-TW | Female | zh-TW-HsiaoChenNeural | General |
| Chinese (Taiwanese Mandarin) | zh-TW | Female | zh-TW-HsiaoYuNeural | General |
| Chinese (Taiwanese Mandarin) | zh-TW | Male | zh-TW-YunJheNeural | General |
| Croatian (Croatia) | hr-HR | Female | hr-HR-GabrijelaNeural | General |
| Croatian (Croatia) | hr-HR | Male | hr-HR-SreckoNeural | General |
| Czech (Czech) | cs-CZ | Female | cs-CZ-VlastaNeural | General |
| Czech (Czech) | cs-CZ | Male | cs-CZ-AntoninNeural | General |
| Danish (Denmark) | da-DK | Female | da-DK-ChristelNeural | General |
| Danish (Denmark) | da-DK | Male | da-DK-JeppeNeural | General |
| Dutch (Belgium) | nl-BE | Female | nl-BE-DenaNeural New | General |
| Dutch (Belgium) | nl-BE | Male | nl-BE-ArnaudNeural New | General |
| Dutch (Netherlands) | nl-NL | Female | nl-NL-ColetteNeural | General |
| Dutch (Netherlands) | nl-NL | Female | nl-NL-FennaNeural | General |
| Dutch (Netherlands) | nl-NL | Male | nl-NL-MaartenNeural | General |
| English (Australia) | en-AU | Female | en-AU-NatashaNeural | General |
| English (Australia) | en-AU | Male | en-AU-WilliamNeural | General |
| English (Canada) | en-CA | Female | en-CA-ClaraNeural | General |
| English (Canada) | en-CA | Male | en-CA-LiamNeural | General |
| English (India) | en-IN | Female | en-IN-NeerjaNeural | General |
| English (India) | en-IN | Male | en-IN-PrabhatNeural | General |
| English (Ireland) | en-IE | Female | en-IE-EmilyNeural | General |
| English (Ireland) | en-IE | Male | en-IE-ConnorNeural | General |
| English (Philippines) | en-PH | Female | en-PH-RosaNeural New | General |
| English (Philippines) | en-PH | Male | en-PH-JamesNeural New | General |
| English (United Kingdom) | en-GB | Female | en-GB-LibbyNeural | General |
| English (United Kingdom) | en-GB | Female | en-GB-MiaNeural | General |
| English (United Kingdom) | en-GB | Male | en-GB-RyanNeural | General |
| English (United States) | en-US | Female | en-US-AriaNeural | General, multiple voice styles available using SSML |
| English (United States) | en-US | Female | en-US-JennyNeural | General |
| English (United States) | en-US | Male | en-US-GuyNeural | General |
| Estonian (Estonia) | et-EE | Female | et-EE-AnuNeural | General |
| Estonian (Estonia) | et-EE | Male | et-EE-KertNeural | General |
| Finnish (Finland) | fi-FI | Female | fi-FI-NooraNeural | General |
| Finnish (Finland) | fi-FI | Female | fi-FI-SelmaNeural | General |
| Finnish (Finland) | fi-FI | Male | fi-FI-HarriNeural | General |
| French (Belgium) | fr-BE | Female | fr-BE-CharlineNeural New | General |
| French (Belgium) | fr-BE | Male | fr-BE-GerardNeural New | General |
| French (Canada) | fr-CA | Female | fr-CA-SylvieNeural | General |
| French (Canada) | fr-CA | Male | fr-CA-AntoineNeural | General |
| French (Canada) | fr-CA | Male | fr-CA-JeanNeural | General |
| French (France) | fr-FR | Female | fr-FR-DeniseNeural | General |
| French (France) | fr-FR | Male | fr-FR-HenriNeural | General |
| French (Switzerland) | fr-CH | Female | fr-CH-ArianeNeural | General |
| French (Switzerland) | fr-CH | Male | fr-CH-FabriceNeural | General |
| German (Austria) | de-AT | Female | de-AT-IngridNeural | General |
| German (Austria) | de-AT | Male | de-AT-JonasNeural | General |
| German (Germany) | de-DE | Female | de-DE-KatjaNeural | General |
| German (Germany) | de-DE | Male | de-DE-ConradNeural | General |
| German (Switzerland) | de-CH | Female | de-CH-LeniNeural | General |
| German (Switzerland) | de-CH | Male | de-CH-JanNeural | General |
| Greek (Greece) | el-GR | Female | el-GR-AthinaNeural | General |
| Greek (Greece) | el-GR | Male | el-GR-NestorasNeural | General |
| Hebrew (Israel) | he-IL | Female | he-IL-HilaNeural | General |
| Hebrew (Israel) | he-IL | Male | he-IL-AvriNeural | General |
| Hindi (India) | hi-IN | Female | hi-IN-SwaraNeural | General |
| Hindi (India) | hi-IN | Male | hi-IN-MadhurNeural | General |
| Hungarian (Hungary) | hu-HU | Female | hu-HU-NoemiNeural | General |
| Hungarian (Hungary) | hu-HU | Male | hu-HU-TamasNeural | General |
| Indonesian (Indonesia) | id-ID | Female | id-ID-GadisNeural | General |
| Indonesian (Indonesia) | id-ID | Male | id-ID-ArdiNeural | General |
| Irish (Ireland) | ga-IE | Female | ga-IE-OrlaNeural | General |
| Irish (Ireland) | ga-IE | Male | ga-IE-ColmNeural | General |
| Italian (Italy) | it-IT | Female | it-IT-ElsaNeural | General |
| Italian (Italy) | it-IT | Female | it-IT-IsabellaNeural | General |
| Italian (Italy) | it-IT | Male | it-IT-DiegoNeural | General |
| Japanese (Japan) | ja-JP | Female | ja-JP-NanamiNeural | General |
| Japanese (Japan) | ja-JP | Male | ja-JP-KeitaNeural | General |
| Korean (Korea) | ko-KR | Female | ko-KR-SunHiNeural | General |
| Korean (Korea) | ko-KR | Male | ko-KR-InJoonNeural | General |
| Latvian (Latvia) | lv-LV | Female | lv-LV-EveritaNeural | General |
| Latvian (Latvia) | lv-LV | Male | lv-LV-NilsNeural | General |
| Lithuanian (Lithuania) | lt-LT | Female | lt-LT-OnaNeural | General |
| Lithuanian (Lithuania) | lt-LT | Male | lt-LT-LeonasNeural | General |
| Malay (Malaysia) | ms-MY | Female | ms-MY-YasminNeural | General |
| Malay (Malaysia) | ms-MY | Male | ms-MY-OsmanNeural | General |
| Maltese (Malta) | mt-MT | Female | mt-MT-GraceNeural | General |
| Maltese (Malta) | mt-MT | Male | mt-MT-JosephNeural | General |
| Norwegian (BokmГҐl, Norway) | nb-NO | Female | nb-NO-IselinNeural | General |
| Norwegian (BokmГҐl, Norway) | nb-NO | Female | nb-NO-PernilleNeural | General |
| Norwegian (BokmГҐl, Norway) | nb-NO | Male | nb-NO-FinnNeural | General |
| Polish (Poland) | pl-PL | Female | pl-PL-AgnieszkaNeural | General |
| Polish (Poland) | pl-PL | Female | pl-PL-ZofiaNeural | General |
| Polish (Poland) | pl-PL | Male | pl-PL-MarekNeural | General |
| Portuguese (Brazil) | pt-BR | Female | pt-BR-FranciscaNeural | General, multiple voice styles available using SSML |
| Portuguese (Brazil) | pt-BR | Male | pt-BR-AntonioNeural | General |
| Portuguese (Portugal) | pt-PT | Female | pt-PT-FernandaNeural | General |
| Portuguese (Portugal) | pt-PT | Female | pt-PT-RaquelNeural | General |
| Portuguese (Portugal) | pt-PT | Male | pt-PT-DuarteNeural | General |
| Romanian (Romania) | ro-RO | Female | ro-RO-AlinaNeural | General |
| Romanian (Romania) | ro-RO | Male | ro-RO-EmilNeural | General |
| Russian (Russia) | ru-RU | Female | ru-RU-DariyaNeural | General |
| Russian (Russia) | ru-RU | Female | ru-RU-SvetlanaNeural | General |
| Russian (Russia) | ru-RU | Male | ru-RU-DmitryNeural | General |
| Slovak (Slovakia) | sk-SK | Female | sk-SK-ViktoriaNeural | General |
| Slovak (Slovakia) | sk-SK | Male | sk-SK-LukasNeural | General |
| Slovenian (Slovenia) | sl-SI | Female | sl-SI-PetraNeural | General |
| Slovenian (Slovenia) | sl-SI | Male | sl-SI-RokNeural | General |
| Spanish (Mexico) | es-MX | Female | es-MX-DaliaNeural | General |
| Spanish (Mexico) | es-MX | Male | es-MX-JorgeNeural | General |
| Spanish (Spain) | es-ES | Female | es-ES-ElviraNeural | General |
| Spanish (Spain) | es-ES | Male | es-ES-AlvaroNeural | General |
| Swedish (Sweden) | sv-SE | Female | sv-SE-HilleviNeural | General |
| Swedish (Sweden) | sv-SE | Female | sv-SE-SofieNeural | General |
| Swedish (Sweden) | sv-SE | Male | sv-SE-MattiasNeural | General |
| Tamil (India) | ta-IN | Female | ta-IN-PallaviNeural | General |
| Tamil (India) | ta-IN | Male | ta-IN-ValluvarNeural | General |
| Telugu (India) | te-IN | Female | te-IN-ShrutiNeural | General |
| Telugu (India) | te-IN | Male | te-IN-MohanNeural | General |
| Thai (Thailand) | th-TH | Female | th-TH-AcharaNeural | General |
| Thai (Thailand) | th-TH | Female | th-TH-PremwadeeNeural | General |
| Thai (Thailand) | th-TH | Male | th-TH-NiwatNeural | General |
| Turkish (Turkey) | tr-TR | Female | tr-TR-EmelNeural | General |
| Turkish (Turkey) | tr-TR | Male | tr-TR-AhmetNeural | General |
| Ukrainian (Ukraine) | uk-UA | Female | uk-UA-PolinaNeural New | General |
| Ukrainian (Ukraine) | uk-UA | Male | uk-UA-OstapNeural New | General |
| Urdu (Pakistan) | ur-PK | Female | ur-PK-UzmaNeural New | General |
| Urdu (Pakistan) | ur-PK | Male | ur-PK-AsadNeural New | General |
| Vietnamese (Vietnam) | vi-VN | Female | vi-VN-HoaiMyNeural | General |
| Vietnamese (Vietnam) | vi-VN | Male | vi-VN-NamMinhNeural | General |
| Welsh (UK) | cy-GB | Female | cy-GB-NiaNeural New | General |
| Welsh (UK) | cy-GB | Male | cy-GB-AledNeural New | General |
Neural voices in preview
Below neural voices are in public preview.
| Language | Locale | Gender | Voice name | Style support |
|---|---|---|---|---|
| Chinese (Mandarin, Simplified) | zh-CN | Female | zh-CN-XiaohanNeural | General, multiple styles available using SSML |
| Chinese (Mandarin, Simplified) | zh-CN | Female | zh-CN-XiaomoNeural | General, multiple role-play and styles available using SSML |
| Chinese (Mandarin, Simplified) | zh-CN | Female | zh-CN-XiaoruiNeural | Senior voice, multiple styles available using SSML |
| Chinese (Mandarin, Simplified) | zh-CN | Female | zh-CN-XiaoxuanNeural | General, multiple role-play and styles available using SSML |
| Chinese (Mandarin, Simplified) | zh-CN | Male | zh-CN-YunxiNeural | General, multiple styles available using SSML |
Voices in public preview are only available in 3 service regions: East US, West Europe and Southeast Asia.
For more information about regional availability, see regions.
To learn how you can configure and adjust neural voices, such as Speaking Styles, see Speech Synthesis Markup Language.
The en-US-JessaNeural voice has changed to en-US-AriaNeural . If you were using «Jessa» before, convert over to «Aria».
You can continue to use the full service name mapping like «Microsoft Server Speech Text to Speech Voice (en-US, AriaNeural)» in your speech synthesis requests.
Standard voices
More than 75 standard voices are available in over 45 languages and locales, which allow you to convert text into synthesized speech. For more information about regional availability, see regions.
With two exceptions, standard voices are created from samples that use a 16 khz sample rate. The en-US-AriaRUS and en-US-GuyRUS voices are also created from samples that use a 24 khz sample rate. All voices can upsample or downsample to other sample rates when synthesizing.
| Language | Locale (BCP-47) | Gender | Voice name |
|---|---|---|---|
| Arabic (Arabic ) | ar-EG | Female | ar-EG-Hoda |
| Arabic (Saudi Arabia) | ar-SA | Male | ar-SA-Naayf |
| Bulgarian (Bulgaria) | bg-BG | Male | bg-BG-Ivan |
| Catalan (Spain) | ca-ES | Female | ca-ES-HerenaRUS |
| Chinese (Cantonese, Traditional) | zh-HK | Male | zh-HK-Danny |
| Chinese (Cantonese, Traditional) | zh-HK | Female | zh-HK-TracyRUS |
| Chinese (Mandarin, Simplified) | zh-CN | Female | zh-CN-HuihuiRUS |
| Chinese (Mandarin, Simplified) | zh-CN | Male | zh-CN-Kangkang |
| Chinese (Mandarin, Simplified) | zh-CN | Female | zh-CN-Yaoyao |
| Chinese (Taiwanese Mandarin) | zh-TW | Female | zh-TW-HanHanRUS |
| Chinese (Taiwanese Mandarin) | zh-TW | Female | zh-TW-Yating |
| Chinese (Taiwanese Mandarin) | zh-TW | Male | zh-TW-Zhiwei |
| Croatian (Croatia) | hr-HR | Male | hr-HR-Matej |
| Czech (Czech Republic) | cs-CZ | Male | cs-CZ-Jakub |
| Danish (Denmark) | da-DK | Female | da-DK-HelleRUS |
| Dutch (Netherlands) | nl-NL | Female | nl-NL-HannaRUS |
| English (Australia) | en-AU | Female | en-AU-Catherine |
| English (Australia) | en-AU | Female | en-AU-HayleyRUS |
| English (Canada) | en-CA | Female | en-CA-HeatherRUS |
| English (Canada) | en-CA | Female | en-CA-Linda |
| English (India) | en-IN | Female | en-IN-Heera |
| English (India) | en-IN | Female | en-IN-PriyaRUS |
| English (India) | en-IN | Male | en-IN-Ravi |
| English (Ireland) | en-IE | Male | en-IE-Sean |
| English (United Kingdom) | en-GB | Male | en-GB-George |
| English (United Kingdom) | en-GB | Female | en-GB-HazelRUS |
| English (United Kingdom) | en-GB | Female | en-GB-Susan |
| English (United States) | en-US | Male | en-US-BenjaminRUS |
| English (United States) | en-US | Male | en-US-GuyRUS |
| English (United States) | en-US | Female | en-US-AriaRUS |
| English (United States) | en-US | Female | en-US-ZiraRUS |
| Finnish (Finland) | fi-FI | Female | fi-FI-HeidiRUS |
| French (Canada) | fr-CA | Female | fr-CA-Caroline |
| French (Canada) | fr-CA | Female | fr-CA-HarmonieRUS |
| French (France) | fr-FR | Female | fr-FR-HortenseRUS |
| French (France) | fr-FR | Female | fr-FR-Julie |
| French (France) | fr-FR | Male | fr-FR-Paul |
| French (Switzerland) | fr-CH | Male | fr-CH-Guillaume |
| German (Austria) | de-AT | Male | de-AT-Michael |
| German (Germany) | de-DE | Female | de-DE-HeddaRUS |
| German (Germany) | de-DE | Male | de-DE-Stefan |
| German (Switzerland) | de-CH | Male | de-CH-Karsten |
| Greek (Greece) | el-GR | Male | el-GR-Stefanos |
| Hebrew (Israel) | he-IL | Male | he-IL-Asaf |
| Hindi (India) | hi-IN | Male | hi-IN-Hemant |
| Hindi (India) | hi-IN | Female | hi-IN-Kalpana |
| Hungarian (Hungary) | hu-HU | Male | hu-HU-Szabolcs |
| Indonesian (Indonesia) | id-ID | Male | id-ID-Andika |
| Italian (Italy) | it-IT | Male | it-IT-Cosimo |
| Italian (Italy) | it-IT | Female | it-IT-LuciaRUS |
| Japanese (Japan) | ja-JP | Female | ja-JP-Ayumi |
| Japanese (Japan) | ja-JP | Female | ja-JP-HarukaRUS |
| Japanese (Japan) | ja-JP | Male | ja-JP-Ichiro |
| Korean (Korea) | ko-KR | Female | ko-KR-HeamiRUS |
| Malay (Malaysia) | ms-MY | Male | ms-MY-Rizwan |
| Norwegian (BokmГҐl, Norway) | nb-NO | Female | nb-NO-HuldaRUS |
| Polish (Poland) | pl-PL | Female | pl-PL-PaulinaRUS |
| Portuguese (Brazil) | pt-BR | Male | pt-BR-Daniel |
| Portuguese (Brazil) | pt-BR | Female | pt-BR-HeloisaRUS |
| Portuguese (Portugal) | pt-PT | Female | pt-PT-HeliaRUS |
| Romanian (Romania) | ro-RO | Male | ro-RO-Andrei |
| Russian (Russia) | ru-RU | Female | ru-RU-EkaterinaRUS |
| Russian (Russia) | ru-RU | Female | ru-RU-Irina |
| Russian (Russia) | ru-RU | Male | ru-RU-Pavel |
| Slovak (Slovakia) | sk-SK | Male | sk-SK-Filip |
| Slovenian (Slovenia) | sl-SI | Male | sl-SI-Lado |
| Spanish (Mexico) | es-MX | Female | es-MX-HildaRUS |
| Spanish (Mexico) | es-MX | Male | es-MX-Raul |
| Spanish (Spain) | es-ES | Female | es-ES-HelenaRUS |
| Spanish (Spain) | es-ES | Female | es-ES-Laura |
| Spanish (Spain) | es-ES | Male | es-ES-Pablo |
| Swedish (Sweden) | sv-SE | Female | sv-SE-HedvigRUS |
| Tamil (India) | ta-IN | Male | ta-IN-Valluvar |
| Telugu (India) | te-IN | Female | te-IN-Chitra |
| Thai (Thailand) | th-TH | Male | th-TH-Pattara |
| Turkish (Turkey) | tr-TR | Female | tr-TR-SedaRUS |
| Vietnamese (Vietnam) | vi-VN | Male | vi-VN-An |
The en-US-Jessa voice has changed to en-US-Aria . If you were using «Jessa» before, convert over to «Aria».
You can continue to use the full service name mapping like «Microsoft Server Speech Text to Speech Voice (en-US, AriaRUS)» in your speech synthesis requests.
Customization
Custom Voice is available in the standard and the neural tier. The languages supported are different for these two tiers.
| Language | Locale | Standard | Neural |
|---|---|---|---|
| Chinese (Mandarin, Simplified) | zh-CN | Yes | Yes |
| Chinese (Mandarin, Simplified), English bilingual | zh-CN bilingual | Yes | Yes |
| English (Australia) | en-AU | No | Yes |
| English (India) | en-IN | Yes | Yes |
| English (United Kingdom) | en-GB | Yes | Yes |
| English (United States) | en-US | Yes | Yes |
| French (Canada) | fr-CA | No | Yes |
| French (France) | fr-FR | Yes | Yes |
| German (Germany) | de-DE | Yes | Yes |
| Italian (Italy) | it-IT | Yes | Yes |
| Japanese (Japan) | ja-JP | No | Yes |
| Korean (Korea) | ko-KR | No | Yes |
| Portuguese (Brazil) | pt-BR | Yes | Yes |
| Spanish (Mexico) | es-MX | Yes | Yes |
| Spanish (Spain) | es-ES | No | Yes |
Select the right locale that matches the training data you have to train a custom voice model. For example, if the recording data you have is spoken in English with a British accent, select en-GB .
We do not support bi-lingual model training in Custom Voice, except for the Chinese-English bi-lingual. Select «Chinese-English bilingual» if you want to train a Chinese voice that can speak English as well. Chinese-English bilingual model training using the standard method is available in North Europe and North Central US only. Custom Neural Voice training is available in UK South and East US.
Speech translation
The Speech Translation API supports different languages for speech-to-speech and speech-to-text translation. The source language must always be from the Speech-to-text language table. The available target languages depend on whether the translation target is speech or text. You may translate incoming speech into more than 60 languages. A subset of languages are available for speech synthesis.
Text languages
| Text language | Language code |
|---|---|
| Afrikaans | af |
| Arabic | ar |
| Bangla | bn |
| Bosnian (Latin) | bs |
| Bulgarian | bg |
| Cantonese (Traditional) | yue |
| Catalan | ca |
| Chinese Simplified | zh-Hans |
| Chinese Traditional | zh-Hant |
| Croatian | hr |
| Czech | cs |
| Danish | da |
| Dutch | nl |
| English | en |
| Estonian | et |
| Fijian | fj |
| Filipino | fil |
| Finnish | fi |
| French | fr |
| German | de |
| Greek | el |
| Gujarati | gu |
| Haitian Creole | ht |
| Hebrew | he |
| Hindi | hi |
| Hmong Daw | mww |
| Hungarian | hu |
| Indonesian | id |
| Irish | ga |
| Italian | it |
| Japanese | ja |
| Kannada | kn |
| Kiswahili | sw |
| Klingon | tlh-Latn |
| Klingon (plqaD) | tlh-Piqd |
| Korean | ko |
| Latvian | lv |
| Lithuanian | lt |
| Malagasy | mg |
| Malay | ms |
| Malayalam | ml |
| Maltese | mt |
| Maori | mi |
| Marathi | mr |
| Norwegian | nb |
| Persian | fa |
| Polish | pl |
| Portuguese (Brazil) | pt-br |
| Portuguese (Portugal) | pt-pt |
| Punjabi | pa |
| Queretaro Otomi | otq |
| Romanian | ro |
| Russian | ru |
| Samoan | sm |
| Serbian (Cyrillic) | sr-Cyrl |
| Serbian (Latin) | sr-Latn |
| Slovak | sk |
| Slovenian | sl |
| Spanish | es |
| Swedish | sv |
| Tahitian | ty |
| Tamil | ta |
| Telugu | te |
| Thai | th |
| Tongan | to |
| Turkish | tr |
| Ukrainian | uk |
| Urdu | ur |
| Vietnamese | vi |
| Welsh | cy |
| Yucatec Maya | yua |
Speaker Recognition
See the following table for supported languages for the various Speaker Recognition APIs. See the overview for additional information on Speaker Recognition.
