Language identification 2.0 Response

Response

The output contains information about the status of the request and about the language/s detected. The information provided is the same for the different output formats and the naming convention used for all fields is snake_case.

Response

These are the fields included in the response document

Name Description

Name	Description
`status`	Contains information about the extraction process and whether it has finished successfully. It is formed by a status code (`code`), a natural number that identifies the result, and a message (`msg`), a string describing the result. In addition, the field (`credits`) contains a natural number that indicates the credits consumed in the request and (`remaining_credits`) shows the number of credits left to the user to get to the credit limit. You can find all the possible status codes returned by the API with an explanation and tips on how to manage them in our error codes catalog. In general, a request is any HTTP request done to the API to analyze less than 500 words. If the text sent is longer than that, then it will be considered that more than a request is made, more specifically, as many requests as we would need if the text were divided in chunks of 500 words. In the case of the Language Identification API, as it serves auxialiary purposes, one requests consumes one credit.
`language_list`	List of detected languages for the document sent. Each element has the following structure: `language`: language detected using the code defined by the ISO639-1 standard. `relevance`: relevance value associated to it. `name`: name of the language. `iso639-3`: three letter code of the ISO639-1 standard. `iso639-2`: two letter code of the ISO639-1 standard. `script`: script used by the language. It will only appear when the `verbose` parameter is enabled. `speakers`: number of speakers. It will only appear when the `verbose` parameter is enabled.

status

Contains information about the extraction process and whether it has finished successfully. It is formed by a status code (code), a natural number that identifies the result, and a message (msg), a string describing the result. In addition, the field (credits) contains a natural number that indicates the credits consumed in the request and (remaining_credits) shows the number of credits left to the user to get to the credit limit.

You can find all the possible status codes returned by the API with an explanation and tips on how to manage them in our error codes catalog.

In general, a request is any HTTP request done to the API to analyze less than 500 words. If the text sent is longer than that, then it will be considered that more than a request is made, more specifically, as many requests as we would need if the text were divided in chunks of 500 words.

In the case of the Language Identification API, as it serves auxialiary purposes, one requests consumes one credit.

language_list

List of detected languages for the document sent. Each element has the following structure:

language: language detected using the code defined by the ISO639-1 standard.
relevance: relevance value associated to it.
name: name of the language.
iso639-3: three letter code of the ISO639-1 standard.
iso639-2: two letter code of the ISO639-1 standard.
script: script used by the language. It will only appear when the verbose parameter is enabled.
speakers: number of speakers. It will only appear when the verbose parameter is enabled.

These are the supported languages:

Name	ISO639-3	ISO639-2	Script	Speakers
Mandarin Chinese	cmn	zh	Han	885000000
Bengali	ben	bn	Bengali	196000000
Japanese	jpn	ja	Hiragana, Katakana, and Han	125000000
Korean	kor	ko	Hangul	75000000
Telugu	tel	te	Telugu	73000000
Tamil	tam	ta	Tamil	62000000
Gujarati	guj	gu	Gujarati	44000000
Malayalam	mal	ml	Malayalam	34014000
Kannada	kan	kn	Kannada	33663000
Burmese	mya	my	Myanmar	31000000
Borana-Arsi-Guji Oromo	gax	or	Latin	30000000
Panjabi	pan	pa	Gurmukhi	25700000
Thai	tha	th	Thai	21000000
Sinhala	sin	si	Sinhala	13218000
Modern Greek	ell	el	Greek	12258540
Central Khmer	khm	km	Khmer	7063200
Armenian	hye	hy	Armenian	6836000
Santali	sat		Ol Chiki	6218900
Tibetan	bod	bo	Tibetan	6150000
Georgian	kat	ka	Georgian	4103000
Lao	lao	lo	Lao	4000000
Sichuan Yi	iii	ii	Yi	1600000
Assyrian Neo-Aramaic	aii		Syriac	1000000
Spanish	spa	es	Latin	332000000
English	eng	en	Latin	322000000
Portuguese	por	pt	Latin	182000000
Indonesian	ind	id	Latin	140000000
French	fra	fr	Latin	124000000
German	deu	de	Latin	121000000
Javanese	jav	jv	Latin	75500800
Vietnamese	vie	vi	Latin	66897000
Italian	ita	it	Latin	63000000
Turkish	tur	tr	Latin	59000000
Polish	pol	pl	Latin	44000000
Swahili	swh	sw	Latin	30000000
Sundanese	sun	su	Latin	27000000
Romanian	ron	ro	Latin	26000000
Hausa	hau	ha	Latin	22000000
Bosnian	bos	bs	Cyrillic	21000000
Croatian	hrv	hr	Latin	21000000
Dutch	nld	nl	Latin	21000000
Serbian	srp	sr	Cyrillic	21000000
Central Kurdish	ckb	ku	Latin	20000000
Yoruba	yor	yo	Latin	20000000
Northern Uzbek	uzn	uz	Cyrillic	18386000
Igbo	ibo	ig	Latin	17000000
Cebuano	ceb		Latin	15230000
Tagalog	tgl	tl	Latin	14850000
Hungarian	hun	hu	Latin	14500000
North Azerbaijani	azj	az	Latin	13869000
Czech	ces	cs	Latin	12000000
Plateau Malagasy	plt	mg	Latin	10156900
Madurese	mad		Latin	10000000
Nyanja	nya	ny	Latin	10000000
Ayacucho Quechua	quy	qu	Latin	1000000
Kinyarwanda	kin	rw	Latin	9306800
Zulu	zul	zu	Latin	9140000
Swedish	swe	sv	Latin	9000000
Lingala	lin	ln	Latin	8400000
Somali	som	so	Latin	8335000
Southern Qiandong Miao	hms		Latin	8200000
Iloko	ilo		Latin	8000000
Uighur	uig	ug	Arabic	7464000
Haitian	hat	ht	Latin	7382000
Akan	aka	ak	Latin	7000000
Hiligaynon	hil		Latin	7000000
Shona	sna	sn	Latin	7000000
Xhosa	xho	xh	Latin	6858000
Minangkabau	min		Latin	6500000
Afrikaans	afr	af	Latin	6365000
Luba-Lulua	lua		Latin	6300000
Finnish	fin	fi	Latin	6000000
Rundi	run	rn	Latin	6000000
Slovak	slk	sk	Latin	5606000
Turkmen	tuk	tk	Cyrillic	5397500
Danish	dan	da	Latin	5292000
Tosk Albanian	als	sq	Latin	5000000
Norwegian Bokmål	nob	nb	Latin	5000000
Sukuma	suk		Latin	5000000
Sango	sag	sg	Latin	4900000
Norwegian Nynorsk	nno	nn	Latin	4700000
Mossi	mos		Latin	4600000
Catalan	cat	ca	Latin	4353000
Southern Sotho	sot	st	Latin	4197000
Central Bikol	bcl		Latin	4000000
Galician	glg	gl	Latin	4000000
Lithuanian	lit	lt	Latin	4000000
Umbundu	umb		Latin	4000000
Tswana	tsn	tn	Latin	3932000
Pedi	nso		Latin	3851000
Balinese	ban		Latin	3800000
Buginese	bug		Latin	3500000
Central Kanuri	knc	kr	Latin	3500000
Ibibio	ibb		Latin	3186000
Ganda	lug	lg	Latin	3015980
Achinese	ace		Latin	3000000
Bambara	bam	bm	Latin	3000000
Kimbundu	kmb		Latin	3000000
Lunda	lun		Latin	3000000
Central Atlas Tamazight	tzm		Latin	3000000
Waray	war		Latin	3000000
Dyula	dyu		Latin	2700000
Wolof	wol	wo	Latin	2700000
Low German	nds		Latin	2600000
Makhuwa	vmw		Latin	2500000
Ewe	ewe	ee	Latin	2477600
Slovenian	slv	sl	Latin	2218000
Central Aymara	ayr	ay	Latin	2200000
Bemba	bem		Latin	2150000
Eastern Maninkakan	emk		Latin	2140300
Baoulé	bci		Latin	2130000
Esperanto	epo	eo	Latin	2000000
Pampanga	pam		Latin	2000000
Tiv	tiv		Latin	2000000
Tok Pisin	tpi		Latin	2000000
Swati	ssw	ss	Latin	1670000
Nyankole	nyn		Latin	1643193
Yao	yao		Latin	1597000
Latvian	lav	lv	Latin	1550000
Vlax Romani	rmy		Latin	1500000
Logudorese Sardinian	src	sc	Latin	1500000
Scots	sco		Latin	1500000
Tsonga	tso	ts	Latin	1500000
Mende	men		Latin	1480000
Fon	fon		Latin	1436000
Central Nahuatl	nhn		Latin	1376898
Northeastern Dinka	dip		Latin	1350000
Makonde	kde		Latin	1260000
Siona	snn		Latin	1240000
Kabiyè	kbp		Latin	1200000
Timne	tem		Latin	1200000
Tonga	toi		Latin	1105000
Estonian	est	et	Latin	1100000
Soninke	snk		Latin	1067000
Chokwe	cjk		Latin	1004000
Adangme	ada		Latin	1000000
Bini	bin		Latin	1000000
Ga	gaa		Latin	1000000
Koongo	kng		Latin	1000000
Ndonga	ndo	ng	Latin	1000000
Balkan Romani	rmn	rm	Latin	1000000
Russian	rus	ru	Cyrillic	288000000
Ukrainian	ukr	uk	Cyrillic	41000000
Komi-Permyak	koi		Cyrillic	12500000
Belarusian	bel	be	Cyrillic	10200000
Bulgarian	bul	bg	Cyrillic	9000000
Kazakh	kaz	kk	Cyrillic	8000000
Tatar	tat	tt	Cyrillic	7000000
Tajik	tgk	tg	Cyrillic	4380000
Kirghiz	kir	ky	Cyrillic	2631420
Macedonian	mkd	mk	Cyrillic	2500000
Halh Mongolian	khk	mn	Cyrillic	2330000
Standard Arabic	arb	ar	Arabic	280000000
Urdu	urd	ur	Arabic	54000000
Seraiki	skr		Arabic	15020000
Iranian Persian	pes	fa	Arabic	7000000
Hindi	hin	hi	Devanagari	182000000
Marathi	mar	mr	Devanagari	64783000
Maithili	mai		Devanagari	34700000
Bhojpuri	bho		Devanagari	25000000
Nepali	nep	ne	Devanagari	16200000
Magahi	mag		Devanagari	10821000
Amharic	amh	am	Ethiopic	23000000
Tigrinya	tir	ti	Ethiopic	6060000
Hebrew	heb	he	Hebrew	4612000
Eastern Yiddish	ydd	yi	Hebrew	3000000

Response examples

The format in which this information will be shown will depend on the value of the of parameter.

New research finds that live music played for premature babies can be beneficial, calming their heart rate and breathing, and helping their sleep and sucking ability.

JSON
XML

{
    status: {
        code: "0",
        msg: "OK",
        credits: "1"
    },
    language_list: [
        {
            language: "en",
            relevance: "100",
            name: "English",
            iso639-3: "eng",
            iso639-2: "en"
        }
    ]
}

<?xml version="1.0" encoding="utf-8"?>
<response>
  <status code="0" credits="1">
    <![CDATA[OK]]>
  </status>
  <language_list>
    <result>
      <language>en</language>
      <relevance>100</relevance>
      <name>English</name>
      <iso6393>eng</iso6393>
      <iso6392>en</iso6392>
    </result>
  </language_list>
</response>