Plum DEV Documentation
developer_reference:tts

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
developer_reference:tts [2019/11/12 11:06]
admin
developer_reference:tts [2020/02/28 14:10] (current)
admin
Line 1: Line 1:
 {{description>​Attributes of the &​lt;​voice&​gt;​ tag and child tags for several Text-to-Speech (TTS) engines. Including audio samples of a selection of TTS voices.}} {{description>​Attributes of the &​lt;​voice&​gt;​ tag and child tags for several Text-to-Speech (TTS) engines. Including audio samples of a selection of TTS voices.}}
 ====== TTS Engine Characteristics ====== ====== TTS Engine Characteristics ======
 +\\ 
 +For details on the Amazon Polly TTS engine, see the corresponding section below.\\
 ===== Voice Tag Attributes ===== ===== Voice Tag Attributes =====
  
Line 13: Line 14:
  
 The gender attribute should not be used if the name attribute is already being used for the <​voice>​ tag. The gender attribute should not be used if the name attribute is already being used for the <​voice>​ tag.
 +
 +__Amazon Polly__
 +
 +This attribute is not supported.
  
 **<​age>:​** **<​age>:​**
Line 25: Line 30:
  
 __RealSpeak Engine:__ __RealSpeak Engine:__
 +
 +This attribute is not supported.
 +
 +__Amazon Polly:__
  
 This attribute is not supported. This attribute is not supported.
Line 129: Line 138:
 </​code>​ </​code>​
  
-NOTE: For US speech recognition,​ we currently only offer American English speech recognition,​ Spanish speech recognition,​ and French-Canadian speech recognition for Plum DEV If you are interested in any other speech recognition languages, please contact your sales representative.+NOTE: For US speech recognition,​ we currently only offer American English speech recognition,​ Spanish speech recognition,​ and French-Canadian speech recognition for Plum DEVIf you are interested in any other speech recognition languages, please contact your sales representative.
  
-NOTE: For UK speech recognition,​ we currently only offer American English speech ​recogition ​and British English speech recognition for Plum DEV If you are interested in any other speech recognition languages, please contact your sales representative.+NOTE: For UK speech recognition,​ we currently only offer American English speech ​recognition ​and British English speech recognition for Plum DEVIf you are interested in any other speech recognition languages, please contact your sales representative. 
 + 
 +__Amazon Polly__ 
 +^ Language ^ Name/ID ^ Gender ^ Standard Voice ^ Neural Voice ^ 
 +| Arabic (arb) | Zeina | Female | Yes | No | 
 +| Chinese, Mandarin (cmn-CN) | Zhiyu | Female | Yes | No | 
 +| Danish (da-DK) | Naja | Female | Yes | No | 
 +|  | Mads | Male | Yes | No | 
 +| Dutch (nl-NL) | Lotte | Female | Yes | No | 
 +| | Ruben | Male | Yes | No | 
 +| English (Australian) (en-AU) | Nicole | Female | Yes | No | 
 +|  | Russell | Male | Yes | No | 
 +| English (British) (en-GB) | Amy | Female | Yes | Yes | 
 +|  | Emma | Female | Yes | Yes | 
 +|  | Brian | Male | Yes | Yes | 
 +| English (Indian) (en-IN) | Aditi* | Female | Yes | No | 
 +|  | Raveena | Female | Yes | No | 
 +| English (US) (en-US) | Ivy | Female (child) | Yes | Yes | 
 +|  | Joanna## | Female | Yes | Yes | 
 +|  | Kendra | Female | Yes | Yes | 
 +|  | Kimberly | Female | Yes | Yes | 
 +|  | Salli | Female | Yes | Yes |  
 +|  | Joey | Male | Yes | Yes | 
 +|  | Justin | Male (child) | Yes | Yes | 
 +|  | Matthew## | Male | Yes | Yes | 
 +| English (Welsh) (en-GB-WLS) | Geraint | Male | Yes | No | 
 +| French (fr-FR) | Céline/​Celine | Female | Yes | No | 
 +|  | Léa | Female | Yes | No | 
 +|  | Mathieu | Male | Yes | No | 
 +| French (Canadian) (fr-CA) | Chantal | Female | Yes | No | 
 +| German (de-DE) | Marlene | Female | Yes | No | 
 +|  | Vicki | Female | Yes | No | 
 +|  | Hans | Male | Yes | No | 
 +| Hindi (hi-IN) | Aditi* | Female | Yes | No | 
 +| Icelandic (is-IS) | Dóra/Dora | Female | Yes | No | 
 +|  | Karl | Male | Yes | No | 
 +| Italian (it-IT) | Carla | Female | Yes | No | 
 +|  | Bianca | Female | Yes | No | 
 +|  | Giorgio | Male | Yes | No | 
 +| Japanese (ja-JP) | Mizuki | Female | Yes | No | 
 +|  | Takumi | Male | Yes | No | 
 +| Korean (ko-KR) | Seoyeon | Female | Yes | No | 
 +| Norwegian (nb-NO) | Liv | Female | Yes | No | 
 +| Polish (pl-PL) | Ewa | Female | Yes | No | 
 +|  | Maja | Female | Yes | No | 
 +|  | Jacek | Male | Yes | No | 
 +|  | Jan | Male | Yes | No | 
 +| Portuguese (Brazilian) (pt-BR) | Camila | Female | Yes | Yes | 
 +|  | Vitória/​Vitoria | Female | Yes | No | 
 +|  | Ricardo | Male | Yes | No | 
 +| Portuguese (European) (pt-PT) | Inês/Ines | Female | Yes | No | 
 +|  | Cristiano | Male | Yes | No | 
 +| Romanian (ro-RO) | Carmen | Female | Yes | No | 
 +| Russian (ru-RU) | Tatyana | Female | Yes | No | 
 +|  | Maxim | Male | Yes | No | 
 +| Spanish (European) (es-ES) | Conchita | Female | Yes | No | 
 +|  | Lucia | Female | Yes | No | 
 +|  | Enrique | Male | Yes | No | 
 +| Spanish (Mexican) (es-MX) | Mia | Female | Yes | No | 
 +| Spanish (US) (es-US) | Lupe | Female | Yes | Yes | 
 +|  | Penélope/​Penelope | Female | Yes | No | 
 +|  | Miguel | Male | Yes | No | 
 +| Swedish (sv-SE) | Astrid | Female | Yes | No | 
 +| Turkish (tr-TR) | Filiz | Female | Yes | No | 
 +| Welsh (cy-GB) | Gwyneth | Female | Yes | No | 
 + 
 +**Note**: 
 +* This voice is bilingual and can speak both English and Hindi. For more information,​ see Bilingual Voices [[https://​docs.aws.amazon.com/​polly/​latest/​dg/​bilingual-voices.html]]. 
 + 
 +## These voices can be used with both the Conversational and Newscaster speaking styles when used with the Neural format. For more information,​ see NTTS Speaking Styles [[https://​docs.aws.amazon.com/​polly/​latest/​dg/​ntts-speakingstyles.html]]. 
 + 
 +==== Voice Selection for Polly ==== 
 + 
 +If the Amazon Polly TTS is specified, and neither a <​speak>​ nor <​voice>​ tag are specified, ​ Plum Voice uses the en_US, standard, female voice Joanna by default. 
 + 
 +=== <​speak>​ === 
 + 
 +The <​speak>​ tag should be used to specify the desired language through the attribute xml:​lang=”//​lg-CN//​”,​ where //lg-CN// is the language-country pair specified in the Language column from that table of supported languages here: https://​docs.aws.amazon.com/​polly/​latest/​dg/​voicelist.html.  
 + 
 +Please note that each voice has an associated language. Selecting a language that is not associated with the voice will result in unpredictable behavior; however, in many cases, you will hear the language the text was written in accented by that voice’s associated language. 
 + 
 +=== <​voice>​ === 
 + 
 +The <​voice>​ tag should be used to specify the desired voice through the attribute name=”//​name//​”,​ where //name// is the voice specified in the Name/ID column for the table of supported voices here: https://​docs.aws.amazon.com/​polly/​latest/​dg/​voicelist.html. 
 + 
 +Within the <​voice>​ tag the attribute variant=”//​number//​” should be used to specify whether a standard voice (variant=1) or neural voice (variant=2) is desired. ​ \\ 
 +\\ 
 +Note that only certain voices support the neural option. ​ See: [[https://​docs.aws.amazon.com/​polly/​latest/​dg/​voicelist.html]] for a list of voices that support neural, and [[https://​docs.aws.amazon.com/​polly/​latest/​dg/​NTTS-main.html]] for the differences between standard and neural voices. 
 + 
 +If another voice is desired, it should specified using the <​speak>​ and <​voice>​ tags as follows within the prompt block:  
 + 
 +<​code>​ 
 +<?xml version="​1.0"?>​ 
 +<vxml version="​2.0">​ 
 + <​form>​ 
 +  <​block>​ 
 +   <​prompt>​ 
 +    <speak xml:​lang=”es-MX”>​ 
 +    <voice name="​Mia"​ variant=”1”>​ 
 +     ​Hello,​ thank you for calling Plum Voice. 
 +    </​voice>​ 
 +    </​speak>​ 
 +   </​prompt>​ 
 +  </​block>​ 
 + </​form>​ 
 +</​vxml>​ 
 +</​code>​ 
 + 
 +To sequentially use multiple languages and voices within a <​prompt>​ block, use multiple <​speak> ​ and <​voice>​ blocks. ​ For example: 
 +<​code>​ 
 +<?xml version="​1.0"?>​ 
 +<vxml version="​2.0">​ 
 + <​form>​ 
 +  <​block>​ 
 +   <​prompt>​ 
 +    <speak xml:​lang="​en-US">​ 
 +    <voice name="​Joanna"​ variant="​2">​ 
 +     Press one to continue in English. 
 +    </​voice>​ 
 +    </​speak>​ 
 +    <speak xml:​lang="​es-US">​ 
 +    <voice name="​Lupe"​ variant="​2">​ 
 +     ​Presione dos para continuar en español. 
 +    </​voice>​ 
 +    </​speak>​  
 +    <speak xml:​lang="​fr-FR">​ 
 +    <voice name="​Celine"​ variant="​standard">​ 
 +     ​Appuyez sur trois pour continuer en français. 
 +    </​voice>​ 
 +    </​speak>​ 
 +   </​prompt>​ 
 +  </​block>​ 
 + </​form>​ 
 +</​vxml>​ 
 +</​code>​
  
 **<​xml:​lang>:​** **<​xml:​lang>:​**
Line 195: Line 338:
 An "​x"​ marks that the Child Tag is supported by the speech engine. An asterisk (*) means that there are notes to explain the difference between the speech engines. ​ An "​x"​ marks that the Child Tag is supported by the speech engine. An asterisk (*) means that there are notes to explain the difference between the speech engines. ​
  
-^ Child Tag    ^ AT&T Natural Voices ^ Cepstral Engine ^ RealSpeak Engine ^  +For more details on these SSML tags as they relate to Amazon Polly, please visit: [[https://​docs.aws.amazon.com/​polly/​latest/​dg/​supportedtags.html]]. **Note** that Plum Voice does not currently support all the tags listed on Amazon'​s website. 
-| <​break>​* ​    ​| ​         x          |        x        |        x         ^ + 
-| <​emphasis> ​  ​| ​                    ​| ​                ​| ​                 ^ +^ Child Tag    ^ AT&T Natural Voices ^ Cepstral Engine ^ RealSpeak Engine ​^ Amazon Polly 
-| <​enumerate> ​ |          x          |        x        |        x         ^ +| <​break>​* ​    ​| ​         x          |        x        |        x         |              ​
-| <​mark> ​      ​| ​                    ​| ​                ​| ​                 ^ +| <​emphasis> ​  ​| ​                    ​| ​                ​| ​                 ​|        x     
-| <​paragraph>​* |          x          |        x        |        x         ^ +| <​enumerate> ​ |          x          |        x        |        x         |              ​
-| <​phoneme>​* ​  ​| ​         x          |                 ​| ​       x         ^ +| <​mark> ​      ​| ​                    ​| ​                ​| ​                 ​|              ​
-| <​prosody>​* ​  ​| ​         x          |        x        |        x         ^ +| <​paragraph>​* |          x          |        x        |        x         |              ​
-| <​say-as>​* ​   |          x          |        x        |        x         ^ +| <​phoneme>​* ​  ​| ​         x          |                 ​| ​       x         |        x     
-| <​sentence>​* ​ |          x          |        x        |        x         ^ +| <​prosody>​* ​  ​| ​         x          |        x        |        x         |        x     
-| <​speak> ​     |          x          |        x        |        x         ^ +| <​say-as>​* ​   |          x          |        x        |        x         |        x     
-| <​sub> ​       |          x          |        x        |        x         ^ +| <​sentence>​* ​ |          x          |        x        |        x         |              ​
-| <​value> ​     |          x          |        x        |        x         ^+| <​speak> ​     |          x          |        x        |        x         |              ​
 +| <​sub> ​       |          x          |        x        |        x         |        x     
 +| <​value> ​     |          x          |        x        |        x         |              ​^
  
 ====<​break>​==== ====<​break>​====
Line 560: Line 705:
  
 ====<​prosody>​==== ====<​prosody>​====
 +__Amazon Polly__:
 +
 +The Amazon Polly engine provides granular control over volume, rate, and pitch. For detailed information about how to use this tag, consult [[https://​docs.aws.amazon.com/​polly/​latest/​dg/​supportedtags.html#​prosody-tag]].
  
 __AT&T Natural Voices__: __AT&T Natural Voices__:
Line 657: Line 805:
  
 The xml:lang attribute does not work with the sentence element. The xml:lang attribute does not work with the sentence element.
-