# Voices in Amazon Polly Amazon Polly provides dozens of lifelike voices and support for a variety of languages. Each voice is created using native language speakers, so there are variations from voice to voice, even within the same language. You can also use the AWS Management Console to test each voice with text of your choice. For most languages, there will be at least one male and one female voice, and often more than one of each. A few languages only have a single voice. The inventory of voices and the number of languages included is continually being updated to include additional choices. To suggest a new language or voice, provide feedback on this page. Unfortunately, we are not able to comment on plans for specific new languages before they are released. **Note** To hear example Amazon Polly voices in your browser, see the [Amazon Polly product overview](https://aws.amazon.com/polly). **Topics** + [ # Available voices ](available-voices.md) + [ # Bilingual voices ](bilingual-voices.md) + [ # Applying the newscaster voice ](newscaster-voices.md) + [ # Listening to voices ](listen-to-voices.md) + [ # Timing a voice speed ](voice-speed-vip.md) + [ # Changing a voice speed ](voice-speed-change-vip.md) # Available voices Amazon Polly provides a variety of lifelike voices in multiple languages for synthesizing speech from text. The following table shows all the voices that Amazon Polly offers. | | Language and language variants | Language code | Name/ID | Gender | Generative voice | Long Form voice | Neural voice | Standard voice | | --- | --- | --- | --- | --- | --- | --- | --- | --- | | 1 | **Arabic** | arb | Zeina | Female | No | No | No | Yes | | 2 | **Arabic (Gulf)** | ar-AE | Hala\$1 Zayd\$1 | Female Male | No No | No No | Yes Yes | No No | | 3 | **Dutch (Belgian)** | nl-BE | Lisa | Female | Yes | No | Yes | No | | 4 | **Catalan** | ca-ES | Arlet | Female | No | No | Yes | No | | 5 | **Czech** | cs-CZ | Jitka | Female | No | No | Yes | No | | 6 | **Chinese (Cantonese)** | yue-CN | Hiujin | Female | No | No | Yes | No | | 7 | **Chinese (Mandarin)** | cmn-CN | Zhiyu | Female | No | No | Yes | Yes | | 8 | **Danish** | da-DK | Naja Mads Sofie | Female Male Female | No No No | No No No | No No Yes | Yes Yes No | | 9 | **Dutch** | nl-NL | Laura Lotte Ruben | Female Female Male | Yes No No | No No No | Yes No No | No Yes Yes | | 10 | **English (Australian)** | en-AU | Nicole Olivia Russell | Female Female Male | No Yes No | No No No | No Yes No | Yes No Yes | | 11 | **English (British)** | en-GB | Amy\$1\$1 Emma Brian Arthur | Female Female Male Male | Yes No Yes No | No No No No | Yes Yes Yes Yes | Yes Yes Yes No | | 12 | **English (Indian)** | en-IN | Aditi\$1 Raveena Kajal\$1 | Female Female Female | No No Yes | No No No | No No Yes | Yes Yes No | | 13 | **English (Ireland)** | en-IE | Niamh | Female | Yes | No | Yes | No | | 14 | **English (New Zealand)** | en-NZ | Aria | Female | Yes | No | Yes | No | | 15 | **English (Singaporean)** | en-SG | Jasmine | Female | Yes | No | Yes | No | | 16 | **English (South African)** | en-ZA | Ayanda | Female | Yes | No | Yes | No | | 17 | **English (US)** | en-US | Danielle Gregory Ivy Joanna\$1\$1 Kendra Kimberly Salli Joey Justin Kevin Matthew\$1\$1 Ruth Stephen Tiffany Patrick | Female Male Female (child) Female Female Female Female Male Male (child) Male (child) Male Female Male Female Male | Yes No No Yes No No Yes No No No Yes Yes Yes Yes No | Yes Yes No No No No No No No No No Yes No No Yes | Yes Yes Yes Yes Yes Yes Yes Yes Yes Yes Yes Yes Yes No No | No No Yes Yes Yes Yes Yes Yes No Yes No No No No No | | 18 | **English (Welsh)** | en-GB-WLS | Geraint | Male | No | No | No | Yes | | 19 | **Finnish** | fi-FI | Suvi | Female | No | No | Yes | No | | 20 | **French** | fr-FR | Ambre Céline/Celine Florian Léa Mathieu Rémi | Female Female Male Female Male Male | Yes Yes Yes Yes No Yes | No No No No No No | No No No Yes No Yes | No Yes No Yes Yes No | | 21 | **French (Belgian)** | fr-BE | Isabelle | Female | Yes | No | Yes | No | | 22 | **French (Canadian)** | fr-CA | Chantal Gabrielle Liam | Female Female Male | No Yes Yes | No No No | No Yes Yes | Yes No No | | 23 | **German** | de-DE | Marlene Vicki Hans Daniel Lennart | Female Female Male Male Male | No Yes No Yes Yes | No No No No No | No Yes No Yes No | Yes Yes Yes No No | | 24 | **German (Austrian)** | de-AT | Hannah | Female | Yes | No | Yes | No | | 25 | **German (Swiss)** | de-CH | Sabrina | Female | Yes | No | Yes | No | | 26 | **Hindi** | hi-IN | Aditi\$1 Kajal\$1 | Female Female | No No | No No | No Yes | Yes No | | 27 | **Icelandic** | is-IS | Dóra/Dora Karl | Female Male | No No | No No | No No | Yes Yes | | 28 | **Italian** | it-IT | Beatrice Carla Bianca Lorenzo Giorgio Adriano | Female Female Female Male Male Male | Yes No Yes Yes No No | No No No No No No | No No Yes No No Yes | No Yes Yes No Yes No | | 29 | **Japanese** | ja-JP | Mizuki Takumi Kazuha Tomoko | Female Male Female Female | No No No No | No No No No | No Yes Yes Yes | Yes Yes No No | | 30 | **Korean** | ko-KR | Seoyeon Jihye | Female Female | Yes No | No No | Yes Yes | Yes No | | 31 | **Norwegian** | nb-NO | Liv Ida | Female Female | No No | No No | No Yes | Yes No | | 32 | **Polish** | pl-PL | Ewa Maja Jacek Jan Ola | Female Female Male Male Female | Yes No No No Yes | No No No No No | No No No No Yes | Yes Yes Yes Yes No | | 33 | **Portuguese (Brazilian)** | pt-BR | Camila Vitória/Vitoria Ricardo Thiago | Female Female Male Male | Yes No No No | No No No No | Yes Yes No Yes | Yes Yes Yes No | | 34 | **Portuguese (European)** | pt-PT | Inês/Ines Cristiano | Female Male | No No | No No | Yes No | Yes Yes | | 35 | **Romanian** | ro-RO | Carmen | Female | No | No | No | Yes | | 36 | **Russian** | ru-RU | Tatyana Maxim | Female Male | No No | No No | No No | Yes Yes | | 37 | **Spanish (Spain)** | es-ES | Conchita Lucia Alba Enrique Sergio Raúl | Female Female Female Male Male Male | No Yes No No Yes No | No No Yes No No Yes | No Yes No No Yes No | Yes Yes No Yes No No | | 38 | **Spanish (Mexican)** | es-MX | Mia Andrés | Female Male | Yes Yes | No No | Yes Yes | Yes No | | 39 | **Spanish (US)** | es-US | Lupe\$1\$1 Penélope/Penelope Miguel Pedro | Female Female Male Male | Yes No No Yes | No No No No | Yes No No Yes | Yes Yes Yes No | | 40 | **Swedish** | sv-SE | Astrid Elin | Female Female | No No | No No | No Yes | Yes No | | 41 | **Turkish** | tr-TR | Filiz Burcu | Female Female | No No | No No | No Yes | Yes No | | 42 | **Welsh** | cy-GB | Gwyneth | Female | No | No | No | Yes | \$1 This voice is bilingual. For more information, see [Bilingual voices](bilingual-voices.md). \$1\$1 These voices can be used with Newscaster speaking styles when used with the Neural format. For more information, see [Applying the newscaster voice](newscaster-voices.md). Each Amazon Polly voice engine has unique features. Learn more about features and Region availability for the voice engines offered by Amazon Polly: + [Generative voices](generative-voices.md) + [Long-form voices](long-form-voices.md) + [Neural voices](neural-voices.md) + [Standard voices](standard-voices.md) ## Brand voices In addition to the available voices listed in the previous table, you can use Amazon Polly to build a custom voice for your brand persona. With a brand voice, you can offer unique and exclusive voices to your customers. To learn more about Amazon Polly brand voices, see [Brand Voice](https://aws.amazon.com/polly/features/#Brand_Voice). # Bilingual voices Amazon Polly has two ways of producing bilingual voices: + [Accented bilingual voices](#accented-bilingual) + [Fully bilingual voices](#true-bilingual) ## Accented bilingual voices Accented bilingual voices can be created using any Amazon Polly voice, but only when using SSML tags. Normally, all words in the input text are spoken in the default language of the voice specified you're using. For example, if you're using the voice of Joanna (who speaks US English), Amazon Polly speaks the following in the Joanna voice without a French accent: ``` Why didn't she just say, 'Je ne parle pas français?' ``` In this case, the words *Je ne parle pas français* are spoken as they would be if they were English. However, if you use the Joanna voice with the tag, Amazon Polly speaks the sentence in the Joanna voice in American-accented French: ``` Why didn't she just say, 'Je ne parle pas français?'. ``` Because Joanna is not a native French voice, pronunciation is based on her native language, US English. For instance, although perfect French pronunciation features an uvual trill /R/ in the word *français*, Joanna's US English voice pronounces this phoneme as the corresponding sound /r/. If you use the voice of Giorgio, who speaks Italian, with the following text, Amazon Polly speaks the sentence in Giorgio's voice with an Italian pronunciation: ``` Mi piace Bruce Springsteen. ``` ## Fully bilingual voices A fully bilingual voice like Aditi or Kajal (Indian English and Hindi) can speak two languages fluently. This gives you the ability to use words and phrases from both languages in a single text using the same voice. Currently, Aditi, Kajal, Hala, and Zayd are the only fully bilingual voices available. **Using a Bilingual Voice (example: Aditi) ** Aditi speaks both Indian English (en-IN) and Hindi (hi-IN) fluently. You can synthesize speech in both English and Hindi, and the voice can switch between the two languages even within the same sentence. Hindi can be used in two different forms: + Devanagari: "उसने कहाँ, खेल तोह अब शुरू होगा" + Romanagari (using the Latin alphabet): "Usne kahan, khel toh ab shuru hoga" Additionally, it's possible to mix English and Hindi of either or both forms within a single sentence: + Devanagari \$1 English: "This is the song कभी कभी अदिति" + Romanagari \$1 English: "This is the song from the movie Jaane Tu Ya Jaane Na." + Devanagari \$1 Romanagari \$1 English: "This is the song कभी कभी अदिति from the movie Jaane Tu Ya Jaane Na." Because Aditi is a bilingual voice, text in all of these cases will be read correctly, as Amazon Polly can differentiate between the languages and scripts. Amazon Polly also supports numbers, dates, times, and currency expansion in both English (Arabic numerals) and Hindi (Devanagari numerals). By default, Arabic numerals are read in Indian English. To make Amazon Polly read them in Hindi, you must use the `hi-IN` language code parameter. # Applying the newscaster voice People use different speaking styles, depending on context. Casual conversation, for example, sounds very different from a TV or radio newscast. Because of the way standard voices are made, they can't produce different speaking styles. However, neural voices can. They can be trained for a specific speaking style, with the variations and emphasis on certain parts of speech inherent in that style. In addition to the default neural voices, Amazon Polly provides a newscaster speaking style that uses the neural system to generate speech in the style of a TV or radio newscaster. The Newscaster style is available with the Matthew and Joanna voices in US English (en-US), the Lupe voice in US Spanish (es-US), and the Amy voice in British English (en-GB). To use the Newscaster style, first choose the neural engine and then use the syntax described in the following steps in your input text. **Note** To use any neural speaking style, you must use one of the AWS Regions that support neural voices. This option is not available in all Regions. For more information, see [Feature and region compatibility](neural-voices.md#ntts-regions). ------ #### [ Console ] **To apply the Newscaster style** 1. Open the Amazon Polly console at [https://console.aws.amazon.com/polly/](https://console.aws.amazon.com/polly/). 1. Make sure that you are using an AWS Region where neural voices are supported. 1. On the Text-to-Speech page, for **Engine**, choose **Neural**. 1. Choose the language and voice you want to use. Only Matthew and Joanna for US English (en-US), Lupe for US Spanish (es-US), and Amy for British English (en-GB) are available in the newscaster voice. 1. Turn on **SSML**. 1. Add input text to your text-to-speech request using the Newscaster style SSML syntax. ``` text ``` For example, you might use the newscaster tag as follows: ``` From the Tuesday, April 16th, 1912 edition of The Guardian newspaper: The maiden voyage of the White Star liner Titanic, the largest ship ever launched ended in disaster. The Titanic started her trip from Southampton for New York on Wednesday. Late on Sunday night she struck an iceberg off the Grand Banks of Newfoundland. By wireless telegraphy she sent out signals of distress, and several liners were near enough to catch and respond to the call. ``` 1. Choose **Listen**. ------ #### [ AWS CLI ] **To apply the Newscaster style** 1. In your API request, include the engine parameter with the `neural` value: ``` --engine neural ``` 1. Add input text to your API request using the Newscaster style SSML syntax. ``` text ``` For example, you might use the newscaster tag as follows: ``` From the Tuesday, April 16th, 1912 edition of The Guardian newspaper: The maiden voyage of the White Star liner Titanic, the largest ship ever launched ended in disaster. The Titanic started her trip from Southampton for New York on Wednesday. Late on Sunday night she struck an iceberg off the Grand Banks of Newfoundland. By wireless telegraphy she sent out signals of distress, and several liners were near enough to catch and respond to the call. ``` ------ For more information about SSML, see [Supported SSML tags](supportedtags.md). # Listening to voices Once you have [set up](getting-started.md) Amazon Polly, you can test voices using custom text on the console. **To listen to Amazon Polly voices on the console** 1. Sign in to the AWS Management Console and open the Amazon Polly console at [https://console.aws.amazon.com/polly/](https://console.aws.amazon.com/polly/). 1. Choose the **Text-to-Speech** tab. 1. For **Engine**, choose **Generative**, **Long Form**, **Neural**, or **Standard**. 1. Select a language and a Region. Then choose a voice. 1. Enter text for the voice to speak or use the default phrase, and then choose **Listen**. # Timing a voice speed Because of the natural variation between voices, each available voice speaks at slightly different speeds. For instance, with US English voices, Ivy and Joanna are slightly faster than Matthew, and considerably faster than Joey. Since there is so much variation between voices, there is no standard speed (words per minute) available for Amazon Polly voices. However, you can find how long it takes for your voice to say the selected text using [Speech Marks](using-speechmarks.md). **To time the length of a spoken text passage** 1. Open the AWS CLI. 1. Run the following code, filling in as needed. ``` aws polly synthesize-speech \ --language-code optional language code if needed --output-format json \ --voice-id [name of desired voice] \ --text '[desired text]' \ --speech-mark-types='["viseme"]' \ LengthOfText.txt ``` 1. Open `LengthOfText.txt`. If the text were "Mary had a little lamb," the last few lines returned by Amazon Polly would be: ``` {"time":882,"type":"viseme","value":"t"} {"time":964,"type":"viseme","value":"a"} {"time":1082,"type":"viseme","value":"p"} ``` The last viseme, essentially the sound for the final letters in "lamb" starts 1082 milliseconds after the beginning of the speech. While this is not exactly the length of the audio, it's close and can serve as the basis for comparison between voices. # Changing a voice speed For certain applications, you may find that you'd prefer the voice you like be slowed down, or speeded up. If the speed of the voice is a concern, Amazon Polly provides the ability to modify this using SSML tags. For example, if your organization was making an application that reads books to immigrant audiences, you may want to vary the voice speed. Your audience may speak English, but their fluency is limited. Amazon Polly helps you slow down the rate of speech using the SSML tag. **You can use a percentage:** ``` In some cases, it might help your audience to slow the speaking rate slightly to aid in comprehension. ``` **Or a preset speed:** ``` In some cases, it might help your audience to slow the speaking rate slightly to aid in comprehension. ``` Two speed options are available to you when using SSML with Amazon Polly: + **Preset speeds:** `x-slow`, `slow`, `medium`, `fast`, and `x-fast`. In these cases, the speed of each option is approximate, depending on your preferred voice. The `medium` option is the normal speed of the voice. + **n% of speech rate:** any percentage of the speech rate, between 20% and 200% can be used. In these cases, you can choose exactly the speed you want. However, the actual speed of the voice is approximate, depending on the voice you've chosen. 100% is considered to be the normal speed of the voice. **Note** Test your selected voice at various speeds. The speed of each option is approximate and depends on the voice you choose. For more information on using the `prosody` tag, see [Controlling volume, speaking rate, and pitch](prosody-tag.md).