Use the language names in the 'name' field, not a shorthand or other identifier.

README.md

@@ -28,7 +28,7 @@
 ----------
 
 The eSpeak NG (Next Generation) Text-to-Speech program is an open source speech
-synthesizer that supports [99 languages and accents](docs/languages.md).
+synthesizer that supports [100 languages and accents](docs/languages.md).
 It is based on the eSpeak engine created by Jonathan Duddington. It uses
 spectral formant synthesis by default which sounds robotic, but can be
 configured to use Klatt formant synthesis or MBROLA to give it a more natural

docs/add_language.md

@@ -159,11 +159,12 @@ Each language needs a language file in `espeak-ng-data/lang` grouped by the
 [language family](#language-family). The filename of the default voice for a
 language should be the same as the language code (e.g. `fr` for French).
 
-
 The simplest voice file would contain just 2 lines to give the language
-name and language code, eg:
+name (from the
+[IANA Language Subtag Registry](https://github.com/rhdunn/bcp47-data/blob/master/language-subtag-registry)
+and language code, e.g.:
 
-	name french
+	name French
 	language fr
 
 This language code specifies which phoneme table and dictionary to use

docs/languages.md

@@ -39,14 +39,15 @@ The supported languages are:
 | `gmw`       | `en-GB-x-gbclan`  | West Germanic         | English                     | Lancastrian            |
 | `gmw`       | `en-GB-x-rp`      | West Germanic         | English                     | Received Pronunciation |
 | `gmw`       | `en-GB-scotland`  | West Germanic         | English                     | Scottish               |
-| `gmw`       | `en-GB-x-gbcwnd`  | West Germanic         | English                     | West Midlands          |
+| `gmw`       | `en-GB-x-gbcwmd`  | West Germanic         | English                     | West Midlands          |
+| `art`       | `eo`              | Constructed           | Esperanto                   |                        |
 | `urj`       | `et`              | Uralic                | Estonian                    |                        |
-| `ira`       | `fa`              | Iranian               | Farsi/Persian<sup>[1]</sup> |                        |
-| `ira`       | `fa-en-us`        | Iranian               | Farsi/Persian<sup>[2]</sup> |                        |
-| `ira`       | `fa-Latin`        | Iranian               | Farsi/Persian<sup>[3]</sup> |                        |
+| `ira`       | `fa`              | Iranian               | Persian<sup>[1]</sup>       |                        |
+| `ira`       | `fa-en-us`        | Iranian               | Persian<sup>[2]</sup>       |                        |
+| `ira`       | `fa-Latn`         | Iranian               | Persian<sup>[3]</sup>       |                        |
 | `urj`       | `fi`              | Uralic                | Finnish                     |                        |
+| `roa`       | `fr-BE`           | Romance               | French                      | Belgium                |
 | `roa`       | `fr`              | Romance               | French                      | France                 |
-| `roa`       | `fr-BE`           | Romance               | French                      | Belgian                |
 | `cel`       | `ga`              | Celtic                | Gaelic                      | Irish                  |
 | `cel`       | `gd`              | Celtic                | Gaelic                      | Scottish               |
 | `ccs`       | `ka`              | South Caucasian       | Georgian                    |                        |
@@ -59,7 +60,7 @@ The supported languages are:
 | `inc`       | `hi`              | Indic                 | Hindi                       |                        |
 | `urj`       | `hu`              | Uralic                | Hungarian                   |                        |
 | `gmq`       | `is`              | North Germanic        | Icelandic                   |                        |
-| `poz`       | `in`              | Malayo-Polynesian     | Indonesian                  |                        |
+| `poz`       | `id`              | Malayo-Polynesian     | Indonesian                  |                        |
 | `art`       | `ia`              | Constructed           | Interlingua                 |                        |
 | `roa`       | `it`              | Romance               | Italian                     |                        |
 | `jpx`       | `jp`              | Japanese              | Japanese<sup>[4]</sup>      |                        |
@@ -88,7 +89,7 @@ The supported languages are:
 | `und`       | `und-fonipa`      |                       | Phonemes<sup>[5]</sup>      | IPA                    |
 | `zls`       | `pl`              | South Slavic          | Polish                      |                        |
 | `roa`       | `pt-BR`           | Romance               | Portuguese                  | Brazillian             |
-| `roa`       | `pt`              | Romance               | Portuguese                  | Portugal               |
+| `roa`       | `pt-PT`           | Romance               | Portuguese                  | Portugal               |
 | `inc`       | `pa`              | Indic                 | Punjabi                     |                        |
 | `roa`       | `ro`              | Romance               | Romanian                    |                        |
 | `zls`       | `ru`              | South Slavic          | Russian                     |                        |

espeak-ng-data/lang/aav/vi

@@ -1,4 +1,4 @@
-name vietnam
+name Vietnamese (Northern)
 language vi
 gender male
 

espeak-ng-data/lang/aav/vi-VN-x-central

@@ -1,4 +1,4 @@
-name vietnam_hue
+name Vietnamese (Central)
 language vi-vn-x-central
 phonemes vi-hue
 dictrules 1

espeak-ng-data/lang/aav/vi-VN-x-south

@@ -1,4 +1,4 @@
-name vietnam_sgn
+name Vietnamese (Southern)
 language vi-vn-x-south
 phonemes vi-sgn
 dictrules 2

espeak-ng-data/lang/art/eo

@@ -1,4 +1,4 @@
-name esperanto
+name Esperanto
 language eo
 gender male
 

espeak-ng-data/lang/art/ia

@@ -1,2 +1,2 @@
-name interlingua
+name Interlingua
 language ia

espeak-ng-data/lang/art/jbo

@@ -1,4 +1,4 @@
-name lojban
+name Lojban
 language jbo
 
 speed 80   // speed adjustment, percentage

espeak-ng-data/lang/art/lfn

@@ -1,4 +1,4 @@
-name lingua_franca_nova
+name Lingua Franca Nova
 language lfn
 gender male
 

espeak-ng-data/lang/azc/nci

@@ -1,4 +1,4 @@
-name nahuatl-classical
+name Nahuatl (Classical)
 language nci
 gender male
 

espeak-ng-data/lang/bat/lt

@@ -1,5 +1,4 @@
-
-name lithuanian
+name Lithuanian
 language lt
 gender male
 

espeak-ng-data/lang/bat/lv

@@ -1,4 +1,4 @@
-name latvian
+name Latvian
 language lv
 gender male
 maintainer Valdis Vitolins <[email protected]>

espeak-ng-data/lang/bnt/sw

@@ -1,4 +1,4 @@
-name swahili
+name Swahili
 language sw
 gender male
 

espeak-ng-data/lang/bnt/tn

@@ -1,4 +1,4 @@
-name setswana
+name Setswana
 language tn
 gender male
 

espeak-ng-data/lang/ccs/ka

@@ -1,2 +1,2 @@
-name georgian
+name Georgian
 language ka

espeak-ng-data/lang/cel/cy

@@ -1,5 +1,5 @@
+name Welsh
 language cy
-name welsh
 gender male
 
 intonation 4

espeak-ng-data/lang/cel/ga

@@ -1,4 +1,4 @@
-name irish-gaeilge
+name Gaelic (Irish)
 language ga
 
 dictrules 1  // fix for eclipsis

espeak-ng-data/lang/cel/gd

@@ -1,4 +1,4 @@
-name scottish-gaelic
+name Gaelic (Scottish)
 language gd
 
 status testing

espeak-ng-data/lang/cus/om

@@ -1,4 +1,4 @@
-name oromo
+name Oromo
 language om
 
 status testing

espeak-ng-data/lang/dra/kn

@@ -1,4 +1,4 @@
-name kannada
+name Kannada
 language kn
 
 intonation 2

espeak-ng-data/lang/dra/ml

@@ -1,4 +1,4 @@
-name malayalam
+name Malayalam
 language ml
 gender male
 

espeak-ng-data/lang/dra/ta

@@ -1,4 +1,4 @@
-name tamil
+name Tamil
 language ta
 gender male
 

espeak-ng-data/lang/dra/te

@@ -1,4 +1,4 @@
-name telugu
+name Telugu
 language te
 
 status testing

espeak-ng-data/lang/esx/kl

@@ -1,3 +1,3 @@
-name greenlandic
+name Greenlandic
 language kl
 

espeak-ng-data/lang/eu

@@ -1,4 +1,4 @@
-name basque
+name Basque
 language eu
 
 status testing

espeak-ng-data/lang/gmq/da

@@ -1,4 +1,4 @@
-name danish
+name Danish
 language da
 gender male
 

espeak-ng-data/lang/gmq/is

@@ -1,4 +1,4 @@
-name icelandic
+name Icelandic
 language is
 gender male
 

espeak-ng-data/lang/gmq/no

@@ -1,4 +1,4 @@
-name norwegian
+name Norwegian
 language no
 language nb
 gender male

espeak-ng-data/lang/gmq/sv

@@ -1,4 +1,4 @@
-name swedish
+name Swedish
 language sv
 gender male
 

espeak-ng-data/lang/gmw/af

@@ -1,4 +1,4 @@
-name afrikaans
+name Afrikaans
 language af
 gender male
 

espeak-ng-data/lang/gmw/de

@@ -1,4 +1,4 @@
-name german
+name German
 language de
 gender male
 

espeak-ng-data/lang/gmw/en

@@ -1,4 +1,4 @@
-name english
+name English (Great Britain)
 language en-gb  2
 language en 2
 gender male

espeak-ng-data/lang/gmw/en-029

@@ -1,4 +1,4 @@
-name en-westindies
+name English (Caribbean)
 language en-029
 language en 10
 gender male

espeak-ng-data/lang/gmw/en-GB-scotland

@@ -1,4 +1,4 @@
-name en-scottish
+name English (Scotland)
 language en-gb-scotland
 language en 4
 gender male

espeak-ng-data/lang/gmw/en-GB-x-gbclan

@@ -1,4 +1,4 @@
-name english-north
+name English (Lancaster)
 language en-gb-x-gbclan
 language en-gb  3
 language en 5

espeak-ng-data/lang/gmw/en-GB-x-gbcwmd

@@ -1,4 +1,4 @@
-name english_wmids
+name English (West Midlands)
 language en-gb-x-gbcwmd
 language en-gb 9
 language en 9

espeak-ng-data/lang/gmw/en-GB-x-rp

@@ -1,4 +1,4 @@
-name english_rp
+name English (Received Pronunciation)
 language en-gb-x-rp
 language en-gb  4
 language en 5

espeak-ng-data/lang/gmw/en-US

@@ -1,4 +1,4 @@
-name english-us
+name English (America)
 language en-us 2
 language en 3
 gender male

espeak-ng-data/lang/gmw/nl

@@ -1,3 +1,3 @@
+name Dutch
 language nl
-name dutch
 gender male

espeak-ng-data/lang/grk/el

@@ -1,4 +1,4 @@
-name greek
+name Greek (Modern)
 language el
 gender male
 

espeak-ng-data/lang/grk/grc

@@ -1,4 +1,4 @@
-name greek-ancient
+name Greek (Ancient)
 language grc
 gender male
 

espeak-ng-data/lang/inc/as

@@ -1,4 +1,4 @@
-name assamese
+name Assamese
 language as
 
 status testing

espeak-ng-data/lang/inc/bn

@@ -1,3 +1,3 @@
-name bengali
+name Bengali
 language bn
 gender male

espeak-ng-data/lang/inc/gu

@@ -1,4 +1,4 @@
-name gujarati
+name Gujarati
 language gu
 
 status testing

espeak-ng-data/lang/inc/hi

@@ -1,3 +1,3 @@
-name hindi
+name Hindi
 language hi
 gender male

espeak-ng-data/lang/inc/kok

@@ -1,2 +1,2 @@
-name konkani
+name Konkani
 language kok

espeak-ng-data/lang/inc/mr

@@ -1,4 +1,4 @@
-name marathi
+name Marathi
 language mr
 
 status testing

espeak-ng-data/lang/inc/ne

@@ -1,4 +1,4 @@
-name nepali
+name Nepali
 language ne
 gender male
 

espeak-ng-data/lang/inc/or

@@ -1,4 +1,4 @@
-name oriya
+name Oriya
 language or
 
 status testing

espeak-ng-data/lang/inc/pa

@@ -1,2 +1,2 @@
-name punjabi
+name Punjabi
 language pa

espeak-ng-data/lang/inc/sd

@@ -1,2 +1,2 @@
-name sindhi
+name Sindhi
 language sd

espeak-ng-data/lang/inc/si

@@ -1,4 +1,4 @@
-name sinhala
+name Sinhala
 language si
 
 status testing

espeak-ng-data/lang/inc/ur

@@ -1,4 +1,4 @@
-name urdu
+name Urdu
 language ur
 maintainer Ejaz Shah <[email protected]>
 status testing

espeak-ng-data/lang/ine/hy

@@ -1,3 +1,3 @@
-name armenian
+name Armenian (East Armenia)
 language hy
 gender male

espeak-ng-data/lang/ine/hy-arevmda

@@ -1,4 +1,4 @@
-name armenian-west
+name Armenian (West Armenia)
 language hy-arevmda
 language hy  8
 gender male

espeak-ng-data/lang/ine/sq

@@ -1,4 +1,4 @@
-name albanian
+name Albanian
 language sq
 gender male
 

espeak-ng-data/lang/ira/fa

@@ -1,6 +1,4 @@
-name Persian+English-UK
+name Persian
 language fa
 maintainer Shadyar Khodayari <[email protected]>
 status mature
-// There is Classic fa file, for person who installs eSpeak using  the ISO-Code of language.
-// This language reads Persian and English with U.K pronunciation, as  Persian uses a collection of  special characters which differs entirely from English characters.

espeak-ng-data/lang/ira/fa-Latn

@@ -1,4 +1,4 @@
-name persian-pinglish
+name Persian (Pinglish)
 // Sometimes, Farsi speakers write Farsi words using English characters, particularly in Chat and SMS (texte messages).), called Pinglish
 language fa-Latn
 maintainer Shadyar Khodayari <[email protected]>

espeak-ng-data/lang/ira/ku

@@ -1,4 +1,4 @@
-name kurdish
+name Kurdish
 language ku
 gender male
 

espeak-ng-data/lang/itc/la

@@ -1,4 +1,4 @@
-name latin
+name Latin
 language la
 gender male
 stressrule 2 33 0 2

espeak-ng-data/lang/jpx/jp

@@ -1,5 +1,5 @@
+name Japanese
 language jp
-name japanese
 phonemes jp
 gender male
 

espeak-ng-data/lang/poz/id

@@ -1,4 +1,4 @@
-name indonesian
+name Indonesian
 language id
 gender male
 

espeak-ng-data/lang/poz/ms

@@ -1,5 +1,5 @@
 // Last updated: 14 October 2010, Jason Ong ([email protected])
-name malay
+name Malay
 language ms
 gender male
 phonemes id

espeak-ng-data/lang/roa/an

@@ -1,3 +1,3 @@
-name aragonese
+name Aragonese
 language an
 gender male

espeak-ng-data/lang/roa/ca

@@ -1,4 +1,4 @@
-name catalan
+name Catalan
 language ca
 gender male
 

espeak-ng-data/lang/roa/es

@@ -1,8 +1,5 @@
-
-name spanish
+name Spanish (Spain)
 language es
 gender male
 dictrules 1
 tunes s6 c6 q6 e6
-
-

espeak-ng-data/lang/roa/es-419

@@ -1,4 +1,4 @@
-name spanish-latin-am
+name Spanish (Latin America)
 language es-419
 language es-mx 6
 language es 6

espeak-ng-data/lang/roa/fr

@@ -1,4 +1,4 @@
-name french
+name French (France)
 language fr-fr
 language fr
 gender male

espeak-ng-data/lang/roa/fr-BE

@@ -1,4 +1,4 @@
-name french-Belgium
+name French (Belgium)
 language fr-be
 language fr 8
 gender male

espeak-ng-data/lang/roa/it

@@ -1,4 +1,4 @@
-name italian
+name Italian
 language it
 gender male
 

espeak-ng-data/lang/roa/pap

@@ -1,4 +1,4 @@
-name papiamento
+name Papiamento
 language pap
 
 status testing

espeak-ng-data/lang/roa/pt-BR

@@ -1,4 +1,4 @@
-name brazil
+name Portuguese (Brazil)
 language pt-br
 language pt
 gender male

espeak-ng-data/lang/roa/pt-PT

@@ -1,4 +1,4 @@
-name portugal
+name Portuguese (Portugal)
 language pt-pt
 language pt 6
 gender male

espeak-ng-data/lang/roa/ro

@@ -1,5 +1,3 @@
-name romanian
+name Romanian
 language ro
 gender male
-
-

espeak-ng-data/lang/sai/gn

@@ -1,5 +1,4 @@
-
-name guarani
+name Guarani
 language gn
 dictrules 1
 words 0 1

espeak-ng-data/lang/sem/am

@@ -1,4 +1,4 @@
-name amharic
+name Amharic
 language am
 
 status testing

espeak-ng-data/lang/sem/ar

@@ -1,4 +1,4 @@
-name arabic
+name Arabic
 language ar
 phonemes ar
 gender male

espeak-ng-data/lang/sem/mt

@@ -1,4 +1,4 @@
-name maltese
+name Maltese
 language mt
 
 status testing

espeak-ng-data/lang/sit/cmn

@@ -1,4 +1,4 @@
-name Mandarin
+name Chinese (Mandarin)
 language zh
 gender male
 words 1
@@ -29,4 +29,4 @@ dict_min 100000
 
 //[en]: replace beginning w with v
 //[zh]: w���v
-//replace 0 w  v
+//replace 0 w  v

espeak-ng-data/lang/sit/mni

@@ -1,2 +1,2 @@
-name manipuri
+name Manipuri
 language mni

espeak-ng-data/lang/sit/my

@@ -1,2 +1,2 @@
-name burmese
+name Burmese
 language my

espeak-ng-data/lang/sit/yue

@@ -1,4 +1,4 @@
-name cantonese
+name Chinese (Cantonese)
 language zh-yue
 language yue
 language zhy

espeak-ng-data/lang/trk/az

@@ -1,4 +1,4 @@
-name azerbaijani
+name Azerbaijani
 language az
 
 status testing

espeak-ng-data/lang/trk/ky

@@ -1,4 +1,4 @@
-name kyrgyz
+name Kyrgyz
 language ky
 
 tunes s3 c3 q3 e3

espeak-ng-data/lang/trk/tr

@@ -1,4 +1,4 @@
-name turkish
+name Turkish
 language tr
 gender male
 

espeak-ng-data/lang/trk/tt

@@ -1,3 +1,3 @@
-name tatar
+name Tatar
 language tt
 gender male

espeak-ng-data/lang/und/und-fonipa

@@ -1,4 +1,4 @@
-name ipa
+name Phonetics (International Phonetic Alphabet)
 language ipa
 
 status testing

espeak-ng-data/lang/urj/et

@@ -1,3 +1,3 @@
-name estonian
+name Estonian
 language et
 

espeak-ng-data/lang/urj/fi

@@ -1,4 +1,4 @@
-name finnish
+name Finnish
 language fi
 gender male
 

espeak-ng-data/lang/urj/hu

@@ -1,4 +1,4 @@
-name hungarian
+name Hungarian
 language hu
 gender male
 option bracket 0 0

espeak-ng-data/lang/zls/bg

@@ -1,5 +1,5 @@
-name bulgarian
+name Bulgarian
 language bg
 
 stressAmp 13 12 17 17 20 22 22 21 
-stressLength 180 170  200 200  200 200  210 220
+stressLength 180 170  200 200  200 200  210 220

espeak-ng-data/lang/zls/bs

@@ -1,4 +1,4 @@
-name bosnian
+name Bosnian
 language bs
 phonemes hr
 dictionary hbs

espeak-ng-data/lang/zls/cs

@@ -1,4 +1,4 @@
-name czech
+name Czech
 language cs
 gender male
 

espeak-ng-data/lang/zls/hr

@@ -1,4 +1,4 @@
-name croatian
+name Croatian
 language hr
 language hbs
 gender male

espeak-ng-data/lang/zls/mk

@@ -1,4 +1,4 @@
-name macedonian
+name Macedonian
 language mk
 gender male
 

espeak-ng-data/lang/zls/pl

@@ -1,4 +1,4 @@
-name polish
+name Polish
 language pl
 gender male
 

espeak-ng-data/lang/zls/ru

@@ -1,4 +1,4 @@
-name russian
+name Russian
 language ru
 gender male
 

espeak-ng-data/lang/zls/sk

@@ -1,4 +1,4 @@
-name slovak
+name Slovak
 language sk
 gender male