| Title: | Call Google's 'Natural Language' API, 'Cloud Translation' API,'Cloud Speech' API and 'Cloud Text-to-Speech' API |
|---|---|
| Description: | Call 'Google Cloud' machine learning APIs for text and speech tasks. Call the 'Cloud Translation' API <https://cloud.google.com/translate/> for detection and translation of text, the 'Natural Language' API <https://cloud.google.com/natural-language/> to analyse text for sentiment, entities or syntax, the 'Cloud Speech' API <https://cloud.google.com/speech/> to transcribe sound files to text and the 'Cloud Text-to-Speech' API <https://cloud.google.com/text-to-speech/> to turn text into sound files. |
| Authors: | Aleksander Dietrichson [ctb], Mark Edmondson [aut, cre], John Muschelli [ctb], Neal Richardson [rev] (Neal reviewed the package for ropensci, see <https://github.com/ropensci/onboarding/issues/127>), Julia Gustavsen [rev] (Julia reviewed the package for ropensci, see <https://github.com/ropensci/onboarding/issues/127>) |
| Maintainer: | Mark Edmondson <[email protected]> |
| License: | MIT + file LICENSE |
| Version: | 0.3.0.9000 |
| Built: | 2025-06-28 06:10:22 UTC |
| Source: | https://github.com/ropensci/googleLanguageR |
Authenticate with Google language API services
gl_auth(json_file)gl_auto_auth(...)gl_auth(json_file)gl_auto_auth(...)
json_file | Authentication json file you have downloaded from your Google Project |
... | additional argument topass to |
The best way to authenticate is to use an environment argument pointing at your authentication file.
Set the file location of your download Google Project JSON file in aGL_AUTH argument
Then, when you load the library you should auto-authenticate
However, you can authenticate directly using this function pointing at your JSON auth file.
## Not run: library(googleLanguageR)gl_auth("location_of_json_file.json")## End(Not run)## Not run: library(googleLanguageR)gl_auto_auth()gl_auto_auth(environment_var = "GAR_AUTH_FILE")## End(Not run)## Not run:library(googleLanguageR)gl_auth("location_of_json_file.json")## End(Not run)## Not run:library(googleLanguageR)gl_auto_auth()gl_auto_auth(environment_var="GAR_AUTH_FILE")## End(Not run)
Analyse text entities, sentiment, syntax and categorisation using the Google Natural Language API
gl_nlp( string, nlp_type = c("annotateText", "analyzeEntities", "analyzeSentiment", "analyzeSyntax", "analyzeEntitySentiment", "classifyText"), type = c("PLAIN_TEXT", "HTML"), language = c("en", "zh", "zh-Hant", "fr", "de", "it", "ja", "ko", "pt", "es"), encodingType = c("UTF8", "UTF16", "UTF32", "NONE"))gl_nlp( string, nlp_type= c("annotateText","analyzeEntities","analyzeSentiment","analyzeSyntax","analyzeEntitySentiment","classifyText"), type= c("PLAIN_TEXT","HTML"), language= c("en","zh","zh-Hant","fr","de","it","ja","ko","pt","es"), encodingType= c("UTF8","UTF16","UTF32","NONE"))
string | A vector of text to detect language for, or Google Cloud Storage URI(s) |
nlp_type | The type of Natural Language Analysis to perform. The default |
type | Whether input text is plain text or a HTML page |
language | Language of source, must be supported by API. |
encodingType | Text encoding that the caller uses to process the output |
string can be a character vector, or a location of a file content on Google cloud Storage.This URI must be of the formgs://bucket_name/object_name
Encoding type can usually be left at defaultUTF8.Read more here
The current language support is availablehere
A list of the following objects, if those fields are asked for vianlp_type:
sentences -Sentences in the input document
tokens -Tokens, along with their syntactic information, in the input document
entities -Entities, along with their semantic information, in the input document
documentSentiment -The overall sentiment for the document
classifyText -Classification of the document
language - The language of the text, which will be the same as the language specified in the request or, if not specified, the automatically-detected language
text - The original text passed into the API.NA if not passed due to being zero-length etc.
https://cloud.google.com/natural-language/docs/reference/rest/v1/documents
## Not run: text <- "to administer medicince to animals is frequently a very difficult matter, and yet sometimes it's necessary to do so"nlp <- gl_nlp(text)nlp$sentencesnlp$tokensnlp$entitiesnlp$documentSentiment## vectorised inputtexts <- c("The cat sat one the mat", "oh no it didn't you fool")nlp_results <- gl_nlp(texts)## End(Not run)## Not run:text<- "to administer medicince to animals is frequently a very difficult matter, and yet sometimes it's necessary to do so"nlp<- gl_nlp(text)nlp$sentencesnlp$tokensnlp$entitiesnlp$documentSentiment## vectorised inputtexts<- c("The cat sat one the mat","oh no it didn't you fool")nlp_results<- gl_nlp(texts)## End(Not run)
Turn audio into text
gl_speech( audio_source, encoding = c("LINEAR16", "FLAC", "MULAW", "AMR", "AMR_WB", "OGG_OPUS", "SPEEX_WITH_HEADER_BYTE"), sampleRateHertz = NULL, languageCode = "en-US", maxAlternatives = 1L, profanityFilter = FALSE, speechContexts = NULL, asynch = FALSE, customConfig = NULL)gl_speech( audio_source, encoding= c("LINEAR16","FLAC","MULAW","AMR","AMR_WB","OGG_OPUS","SPEEX_WITH_HEADER_BYTE"), sampleRateHertz=NULL, languageCode="en-US", maxAlternatives=1L, profanityFilter=FALSE, speechContexts=NULL, asynch=FALSE, customConfig=NULL)
audio_source | File location of audio data, or Google Cloud Storage URI |
encoding | Encoding of audio data sent |
sampleRateHertz | Sample rate in Hertz of audio data. Valid values |
languageCode | Language of the supplied audio as a |
maxAlternatives | Maximum number of recognition hypotheses to be returned. |
profanityFilter | If |
speechContexts | An optional character vector of context to assist the speech recognition |
asynch | If your |
customConfig | [optional] A |
Google Cloud Speech API enables developers to convert audio to text by applying powerfulneural network models in an easy to use API.The API recognizes over 80 languages and variants, to support your global user base.You can transcribe the text of users dictating to an application’s microphone,enable command-and-control through voice, or transcribe audio files, among many other use cases.Recognize audio uploaded in the request, and integrate with your audio storage on Google Cloud Storage,by using the same technology Google uses to power its own products.
A list of two tibbles:$transcript, a tibble of thetranscript with aconfidence;$timings, a tibble that containsstartTime,endTime perword. If maxAlternatives is greater than 1, then the transcript will return near-duplicate rows with other interpretations of the text.Ifasynch is TRUE, then an operation you will need to pass togl_speech_op to get the finished result.
Audio encoding of the data sent in the audio message. All encodings support only 1 channel (mono) audio.Only FLAC and WAV include a header that describes the bytes of audio that follow the header.The other encodings are raw audio bytes with no header.For best results, the audio source should be captured and transmitted using alossless encoding (FLAC or LINEAR16).Recognition accuracy may be reduced if lossy codecs, which include the other codecs listed in this section,are used to capture or transmit the audio, particularly if background noise is present.
Read more on audio encodings herehttps://cloud.google.com/speech/docs/encoding
startTime - Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word.
endTime - Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word.
word - The word corresponding to this set of information.
https://cloud.google.com/speech/reference/rest/v1/speech/recognize
## Not run: test_audio <- system.file("woman1_wb.wav", package = "googleLanguageR")result <- gl_speech(test_audio)result$transcriptresult$timingsresult2 <- gl_speech(test_audio, maxAlternatives = 2L)result2$transcriptresult_brit <- gl_speech(test_audio, languageCode = "en-GB")## make an asynchronous API request (mandatory for sound files over 60 seconds)asynch <- gl_speech(test_audio, asynch = TRUE)## Send to gl_speech_op() for status or finished resultgl_speech_op(asynch)## Upload to GCS bucket for long files > 60 secondstest_gcs <- "gs://mark-edmondson-public-files/googleLanguageR/a-dream-mono.wav"gcs <- gl_speech(test_gcs, sampleRateHertz = 44100L, asynch = TRUE)gl_speech_op(gcs)## Use a custom configurationmy_config <- list(encoding = "LINEAR16", diarizationConfig = list( enableSpeakerDiarization = TRUE, minSpeakerCount = 2, maxSpeakCount = 3 ))# languageCode is required, so will be added if not in your custom configgl_speech(my_audio, languageCode = "en-US", customConfig = my_config)## End(Not run)## Not run:test_audio<- system.file("woman1_wb.wav", package="googleLanguageR")result<- gl_speech(test_audio)result$transcriptresult$timingsresult2<- gl_speech(test_audio, maxAlternatives=2L)result2$transcriptresult_brit<- gl_speech(test_audio, languageCode="en-GB")## make an asynchronous API request (mandatory for sound files over 60 seconds)asynch<- gl_speech(test_audio, asynch=TRUE)## Send to gl_speech_op() for status or finished resultgl_speech_op(asynch)## Upload to GCS bucket for long files > 60 secondstest_gcs<-"gs://mark-edmondson-public-files/googleLanguageR/a-dream-mono.wav"gcs<- gl_speech(test_gcs, sampleRateHertz=44100L, asynch=TRUE)gl_speech_op(gcs)## Use a custom configurationmy_config<- list(encoding="LINEAR16", diarizationConfig= list( enableSpeakerDiarization=TRUE, minSpeakerCount=2, maxSpeakCount=3))# languageCode is required, so will be added if not in your custom configgl_speech(my_audio, languageCode="en-US", customConfig= my_config)## End(Not run)
For asynchronous calls of audio over 60 seconds, this returns the finished job
gl_speech_op(operation = .Last.value)gl_speech_op(operation= .Last.value)
operation | A speech operation object fromgl_speech when |
If the operation is still running, another operation object. If done, the result as pergl_speech
## Not run: test_audio <- system.file("woman1_wb.wav", package = "googleLanguageR")## make an asynchronous API request (mandatory for sound files over 60 seconds)asynch <- gl_speech(test_audio, asynch = TRUE)## Send to gl_speech_op() for status or finished resultgl_speech_op(asynch)## End(Not run)## Not run:test_audio<- system.file("woman1_wb.wav", package="googleLanguageR")## make an asynchronous API request (mandatory for sound files over 60 seconds)asynch<- gl_speech(test_audio, asynch=TRUE)## Send to gl_speech_op() for status or finished resultgl_speech_op(asynch)## End(Not run)
Synthesizes speech synchronously: receive results after all text input has been processed.
gl_talk( input, output = "output.wav", languageCode = "en", gender = c("SSML_VOICE_GENDER_UNSPECIFIED", "MALE", "FEMALE", "NEUTRAL"), name = NULL, audioEncoding = c("LINEAR16", "MP3", "OGG_OPUS"), speakingRate = 1, pitch = 0, volumeGainDb = 0, sampleRateHertz = NULL, inputType = c("text", "ssml"), effectsProfileIds = NULL)gl_talk( input, output="output.wav", languageCode="en", gender= c("SSML_VOICE_GENDER_UNSPECIFIED","MALE","FEMALE","NEUTRAL"), name=NULL, audioEncoding= c("LINEAR16","MP3","OGG_OPUS"), speakingRate=1, pitch=0, volumeGainDb=0, sampleRateHertz=NULL, inputType= c("text","ssml"), effectsProfileIds=NULL)
input | The text to turn into speech |
output | Where to save the speech audio file |
languageCode | The language of the voice as a |
gender | The gender of the voice, if available |
name | Name of the voice, see list viagl_talk_languages for supported voices. Set to |
audioEncoding | Format of the requested audio stream |
speakingRate | Speaking rate/speed between |
pitch | Speaking pitch between |
volumeGainDb | Volumne gain in dB |
sampleRateHertz | Sample rate for returned audio |
inputType | Choose between |
effectsProfileIds | Optional. An identifier which selects 'audio effects' profiles that are applied on (post synthesized) text to speech. Effects are applied on top of each other in the order they are given |
Requires the Cloud Text-To-Speech API to be activated for your Google Cloud project.
Supported voices are herehttps://cloud.google.com/text-to-speech/docs/voices and can be imported into R viagl_talk_languages
To play the audio in code via a browser seegl_talk_player
To use Speech Synthesis Markup Language (SSML) selectinputType=ssml - more details on using this to insert pauses, sounds and breaks in your audio can be found here:https://cloud.google.com/text-to-speech/docs/ssml
To use audio profiles, supply a character vector of the available audio profiles listed here:https://cloud.google.com/text-to-speech/docs/audio-profiles - the audio profiles are applied in the order given. For instanceeffectsProfileIds="wearable-class-device" will optimise output for smart watches,effectsProfileIds=c("wearable-class-device","telephony-class-application") will apply sound filters optimised for smart watches, then telephonic devices.
The file output name you supplied asoutput
https://cloud.google.com/text-to-speech/docs/
## Not run: library(magrittr)gl_talk("The rain in spain falls mainly in the plain", output = "output.wav")gl_talk("Testing my new audio player") %>% gl_talk_player()# using SSMLgl_talk('<speak>The <say-as interpret-as=\"characters\">SSML</say-as> standard <break time=\"1s\"/>is defined by the <sub alias=\"World Wide Web Consortium\">W3C</sub>.</speak>', inputType = "ssml")# using effects profilesgl_talk("This sounds great on headphones", effectsProfileIds = "headphone-class-device")## End(Not run)## Not run:library(magrittr)gl_talk("The rain in spain falls mainly in the plain", output="output.wav")gl_talk("Testing my new audio player")%>% gl_talk_player()# using SSMLgl_talk('<speak>The<say-as interpret-as=\"characters\">SSML</say-as> standard<break time=\"1s\"/>is defined by the<sub alias=\"World Wide Web Consortium\">W3C</sub>.</speak>', inputType="ssml")# using effects profilesgl_talk("This sounds great on headphones", effectsProfileIds="headphone-class-device")## End(Not run)
Returns a list of voices supported for synthesis.
gl_talk_languages(languageCode = NULL)gl_talk_languages(languageCode=NULL)
languageCode | A |
This uses HTML5 audio tags to play audio in your browser
gl_talk_player(audio = "output.wav", html = "player.html")gl_talk_player(audio="output.wav", html="player.html")
audio | The file location of the audio file. Must be supported by HTML5 |
html | The html file location that will be created host the audio |
A platform neutral way to play audio is not easy, so this uses your browser to play it instead.
## Not run: gl_talk("Testing my new audio player") %>% gl_talk_player()## End(Not run)## Not run:gl_talk("Testing my new audio player")%>% gl_talk_player()## End(Not run)
Call viashiny::callModule(gl_talk_shiny, "your_id")
gl_talk_shiny( input, output, session, transcript, ..., autoplay = TRUE, controls = TRUE, loop = FALSE, keep_wav = FALSE)gl_talk_shiny( input, output, session, transcript,..., autoplay=TRUE, controls=TRUE, loop=FALSE, keep_wav=FALSE)
input | shiny input |
output | shiny output |
session | shiny session |
transcript | The (reactive) text to talk |
... | Arguments passed on to
|
autoplay | passed to the HTML audio player - default |
controls | passed to the HTML audio player - default |
loop | passed to the HTML audio player - default |
keep_wav | keep the generated wav files if TRUE. |
Speak in Shiny module (ui)
gl_talk_shinyUI(id)gl_talk_shinyUI(id)
id | The Shiny id |
Shiny Module for use withgl_talk_shiny.
Translate character vectors via the Google Translate API
gl_translate( t_string, target = "en", format = c("text", "html"), source = "", model = c("nmt", "base"))gl_translate( t_string, target="en", format= c("text","html"), source="", model= c("nmt","base"))
t_string | A character vector of text to detect language for |
target | The target language |
format | Whether the text is plain or HTML |
source | Specify the language to translate from. Will detect it if left default |
model | What translation model to use |
You can translate a vector of strings, although if too many for one call then it will bebroken up into one API call per element.This is the same cost as charging is per character translated, but will take longer.
If translating HTML set theformat = "html".Consider removing anything not needed to be translated first,such as JavaScript and CSS scripts. See example on how to do this withrvest
The API limits in three ways: characters per day, characters per 100 seconds,and API requests per 100 seconds.All can be set in the API managerhttps://console.developers.google.com/apis/api/translate.googleapis.com/quotas
A tibble oftranslatedText anddetectedSourceLanguageandtext of length equal to the vector of text you passed in.
https://cloud.google.com/translate/docs/reference/translate
Other translations:gl_translate_detect(),gl_translate_languages()
## Not run: text <- "to administer medicine to animals is frequently a very difficult matter, and yet sometimes it's necessary to do so"gl_translate(text, target = "ja")# translate webpages using rvest to process beforehandlibrary(rvest)library(googleLanguageR)# translate webpages# dr.dk articlemy_url <- "http://bit.ly/2yhrmrH"## in this case the content to translate is in css selector '.wcms-article-content'read_html(my_url) %>% html_node(css = ".wcms-article-content") %>% html_text %>% gl_translate(format = "html")## End(Not run)## Not run:text<- "to administer medicine to animals is frequently a very difficult matter, and yet sometimes it's necessary to do so"gl_translate(text, target="ja")# translate webpages using rvest to process beforehandlibrary(rvest)library(googleLanguageR)# translate webpages# dr.dk articlemy_url<-"http://bit.ly/2yhrmrH"## in this case the content to translate is in css selector '.wcms-article-content'read_html(my_url)%>% html_node(css=".wcms-article-content")%>% html_text%>% gl_translate(format="html")## End(Not run)
Detect the language of text within a request
gl_translate_detect(string)gl_translate_detect(string)
string | A character vector of text to detect language for |
Consider usinglibrary(cld2) andcld2::detect_language instead offline,since that is free and local without needing a paid API call.
gl_translate also returns a detection of the language,so you could also wish to do it in one step via that function.
A tibble of the detected languages with columnsconfidence,isReliable,language, andtext of length equal to the vector of text you passed in.
https://cloud.google.com/translate/docs/reference/detect
Other translations:gl_translate_languages(),gl_translate()
## Not run: gl_translate_detect("katten sidder på måtten")# Detecting language: 39 characters - katten sidder på måtten...# confidence isReliable language text# 1 0.536223 FALSE da katten sidder på måtten## End(Not run)## Not run:gl_translate_detect("katten sidder på måtten")# Detecting language: 39 characters - katten sidder på måtten...# confidence isReliable language text# 1 0.536223 FALSE da katten sidder på måtten## End(Not run)
Translate a document via the Google Translate API
gl_translate_document( d_path, target = "es-ES", output_path = "out.pdf", format = c("pdf"), source = "en-UK", model = c("nmt", "base"), location = "global")gl_translate_document( d_path, target="es-ES", output_path="out.pdf", format= c("pdf"), source="en-UK", model= c("nmt","base"), location="global")
d_path | path of the document to be translated |
output_path | where to save the translated document |
format | currently only pdf-files are supported |
output filename
Other translations:gl_translate_detect(),gl_translate_languages(),gl_translate()
## Not run: gl_translate_document(system.file(package = "googleLanguageR","test-doc.pdf"), "no")## End(Not run)## Not run:gl_translate_document(system.file(package="googleLanguageR","test-doc.pdf"),"no")## End(Not run)
Returns a list of supported languages for translation.
gl_translate_languages(target = "en")gl_translate_languages(target="en")
target | If specified, language names are localized in target language |
Supported language codes, generally consisting of its ISO 639-1 identifier. (E.g.'en', 'ja').In certain cases, BCP-47 codes including language + region identifiers are returned (e.g.'zh-TW', 'zh-CH')
A tibble of supported languages
https://cloud.google.com/translate/docs/reference/languages
Other translations:gl_translate_detect(),gl_translate_document(),gl_translate()
## Not run: # default english names of languages supportedgl_translate_languages()# specify a language code to get other names, such as Danishgl_translate_languages("da")## End(Not run)## Not run:# default english names of languages supportedgl_translate_languages()# specify a language code to get other names, such as Danishgl_translate_languages("da")## End(Not run)
This package contains functions for analysing language through theGoogle Cloud Machine Learning APIs
For examples and documentation see the vignettes and the website:
http://code.markedmondson.me/googleLanguageR/
https://cloud.google.com/products/machine-learning/