Type:	Package
Title:	Text to Speech Conversion
Description:	Converts text into speech using various text-to-speech (TTS) engines and provides an unified interface for accessing their functionality. With this package, users can easily generate audio files of spoken words, phrases, or sentences from plain text data. The package supports multiple TTS engines, including Google's 'Cloud Text-to-Speech API', 'Amazon Polly', Microsoft's 'Cognitive Services Text to Speech REST API', and a free TTS engine called 'Coqui TTS'.
Version:	1.0.0
License:	GPL-3
Suggests:	aws.polly, covr, patrick, rmarkdown, stringi, testthat (≥ 3.0.0)
Encoding:	UTF-8
VignetteBuilder:	knitr
RoxygenNote:	7.2.3
URL:	https://github.com/jhudsl/text2speech
BugReports:	https://github.com/jhudsl/text2speech/issues
Imports:	aws.signature, cli, dplyr, googleAuthR, googleLanguageR, knitr, magrittr, conrad, tidyr, tuneR, utils, withr
Config/testthat/edition:	3
NeedsCompilation:	no
Packaged:	2023-07-19 16:12:31 UTC; howardbaek
Author:	Howard Baek [cre], John Muschelli [aut, ctb]
Maintainer:	Howard Baek <howardbaek.fh@gmail.com>
Repository:	CRAN
Date/Publication:	2023-07-19 22:10:02 UTC

text2speech: Text to Speech Conversion

Description

Converts text into speech using various text-to-speech (TTS) engines and provides an unified interface for accessing their functionality. With this package, users can easily generate audio files of spoken words, phrases, or sentences from plain text data. The package supports multiple TTS engines, including Google's 'Cloud Text-to-Speech API', 'Amazon Polly', Microsoft's 'Cognitive Services Text to Speech REST API', and a free TTS engine called 'Coqui TTS'.

Author(s)

Maintainer: Howard Baek howardbaek.fh@gmail.com (ORCID)

Authors:

• John Muschelli muschellij2@gmail.com (ORCID) [contributor]

See Also

Useful links:

• https://github.com/jhudsl/text2speech

• Report bugs at https://github.com/jhudsl/text2speech/issues

Pipe operator

Description

See ⁠magrittr::[\%>\%][magrittr::\%>\%]⁠ for details.

Usage

lhs %>% rhs

Convert PCM to WAV

Description

Accepts PCM audio data as input and generates a corresponding WAV file

Usage

pcm_to_wav(
  input,
  output = tempfile(fileext = ".wav"),
  sample_rate = 16000,
  extensible = FALSE
)

Arguments

Value

A filename of the output

Examples

## Not run: 
fname = system.file("extdata", "pcm_file.wav", package = "text2speech")
res = pcm_to_wav(fname)
testthat::expect_error(tuneR::readWave(fname))
testthat::expect_is(tuneR::readWave(res), "Wave")

## End(Not run)
## Not run: 
if (requireNamespace("aws.polly", quietly = TRUE)) {
text = "hey, ho, let's go!"
if (tts_amazon_auth()) {
   res = tts_amazon(text, output_format = "wav")
}
}

## End(Not run)

Play audio in a browser

Description

This uses HTML5 audio tags to play audio in your browser.

Usage

play_audio(audio = "output.wav", html = "player.html")

Arguments

Details

Borrowed from googleLanguageR::gl_talk_player()

Examples

## Not run: 
  play_audio(audio = "audio.wav", html = "player.html")

## End(Not run)

Point to local coqui tts Executable File

Description

Function to set an option that points to the local coqui tts Executable File tts.

Usage

set_coqui_path(path)

Arguments

Details

List of possible file path locations for the local coqui tts Executable File

Linux

/usr/bin/tts, /usr/local/bin/tts

Mac

/opt/homebrew/Caskroom/miniforge/base/bin/tts

Windows

C:\Program Files\tts

Value

Returns nothing, function sets the option variable path_to_coqui.

Examples

set_coqui_path("~/path/to/tts")

Text-to-Speech (Speech Synthesis)

Description

Convert text-to-speech using various engines, including Amazon Polly, Coqui TTS, Google Cloud Text-to-Speech API, and Microsoft Cognitive Services Text to Speech REST API.

With the exception of Coqui TTS, all these engines are accessible as R packages:

• aws.polly is a client for Amazon Polly.

• googleLanguageR is a client to the Google Cloud Text-to-Speech API.

• conrad is a client to the Microsoft Cognitive Services Text to Speech REST API

Usage

tts(
  text,
  output_format = c("mp3", "wav"),
  service = c("amazon", "google", "microsoft", "coqui"),
  bind_audio = TRUE,
  ...
)

tts_amazon(
  text,
  output_format = c("mp3", "wav"),
  voice = "Joanna",
  bind_audio = TRUE,
  save_local = FALSE,
  save_local_dest = NULL,
  ...
)

tts_google(
  text,
  output_format = c("mp3", "wav"),
  voice = "en-US-Standard-C",
  bind_audio = TRUE,
  save_local = FALSE,
  save_local_dest = NULL,
  ...
)

tts_microsoft(
  text,
  output_format = c("mp3", "wav"),
  voice = NULL,
  bind_audio = TRUE,
  save_local = FALSE,
  save_local_dest = NULL,
  ...
)

tts_coqui(
  text,
  exec_path,
  output_format = c("wav", "mp3"),
  model_name = "tacotron2-DDC_ph",
  vocoder_name = "ljspeech/univnet",
  bind_audio = TRUE,
  save_local = FALSE,
  save_local_dest = NULL,
  ...
)

Arguments

Value

A standardized tibble featuring the following columns:

• index : Sequential identifier number

• original_text : The text input provided by the user

• text : In case original_text exceeds the character limit, text represents the outcome of splitting original_text. Otherwise, text remains the same as original_text.

• wav : Wave object (S4 class)

• file : File path to the audio file

• audio_type : The audio format, either mp3 or wav

• duration : The duration of the audio file

• service : The text-to-speech engine used

Examples

## Not run: 
# Amazon Polly
tts("Hello world! This is Amazon Polly", service = "amazon")

tts("Hello world! This is Coqui TTS", service = "coqui")

tts("Hello world! This is Google Cloud", service = "google")

tts("Hello world! This is Microsoft", service = "microsoft")

## End(Not run)

Authentication for Text-to-Speech (Speech Synthesis) Engines

Description

Verify the authentication status of different text-to-speech engines, including Amazon Polly, Coqui TTS, Google Cloud Text-to-Speech API, and Microsoft Cognitive Services Text to Speech REST API.

Usage

tts_auth(
  service = c("amazon", "google", "microsoft", "coqui"),
  key_or_json_file = NULL,
  ...
)

tts_amazon_auth(key_or_json_file = NULL, ...)

tts_google_auth(key_or_json_file = NULL, ...)

tts_microsoft_auth(key_or_json_file = NULL, ...)

tts_coqui_auth()

Arguments

Details

To determine the availability of Coqui TTS, tts_auth() examines whether the tts executable exists on local system.

Value

A logical indicator of authorization

Examples

# Amazon Polly
tts_auth("amazon")

# Google Cloud Text-to-Speech API
tts_auth("google")

# Microsoft Cognitive Services Text to Speech REST API
tts_auth("microsoft")

# Coqui TTS
tts_auth("coqui")

Bind WAVs together

Description

As the data are split due to limits of the API, tts_bind_wav() allows the text and the results to be harmonized

Usage

tts_bind_wav(result, same_sample_rate = TRUE)

Arguments

Value

A data.frame with the same structure as that of tts

Examples

## Not run: 
# Same sample rate
tts_bind_wav(res, same_sample_rate = TRUE)

# Different sample rate
tts_bind_wav(res, same_sample_rate = FALSE)


## End(Not run)

Default voice for text-to-speech engine

Description

Default voice for text-to-speech engine

Usage

tts_default_voice(service = c("amazon", "google", "microsoft", "coqui"))

Arguments

Speak Engine for knitr

Description

Speak Engine for knitr

Usage

tts_speak_engine(options)

Arguments

Value

A character string generated from the source code and output using the appropriate output hooks.

Examples

## Not run: 
knitr::knit_engines$set(speak = tts_speak_engine)
options = list(
code = "hey let's go to the park",
eval = FALSE,
label = "random",
fig.path = tempdir(),
echo = TRUE, results = "asis",
engine = "speak")
tts_speak_engine(options)
    if (tts_auth("google")) {
       options$eval = TRUE
       tts_speak_engine(options)
    }

## End(Not run)

Text-to-Speech (Speech Synthesis) Voices

Description

Various services offer a range of voice options:

• Amazon Polly : https://docs.aws.amazon.com/polly/latest/dg/voicelist.html

• Microsoft Cognitive Services Text to Speech REST API : https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/language-support?tabs=tts#voice-styles-and-roles

• Google Cloud Text-to-Speech API : https://cloud.google.com/text-to-speech/docs/voices

• Coqui TTS : https://huggingface.co/spaces/coqui/CoquiTTS

Usage

tts_voices(service = c("amazon", "google", "microsoft", "coqui"), ...)

tts_amazon_voices(...)

tts_microsoft_voices(region = "westus")

tts_google_voices(...)

tts_coqui_voices()

Arguments

Value

(Amazon, Microsoft, and Google) A standardized data.frame featuring the following columns:

• voice : Name of the voice

• language : Spoken language

• language_code : Abbreviation for the language of the speaker

• gender : Male or female

• service : The text-to-speech engine used

(Coqui TTS) A tibble featuring the following columns:

• language : Spoken language

• dataset : Dataset the deep learning model was trained on

• model_name : Name of deep learning model

• service : The text-to-speech engine used

Examples

# Amazon Polly
if (tts_auth(service = "amazon")) {
tts_voices(service = "amazon")
}


# Microsoft Cognitive Services Text to Speech REST API
if (tts_auth(service = "microsoft")) {
tts_voices(service = "microsoft")
}

# Google Cloud Text-to-Speech API
if (tts_auth(service = "google")) {
tts_voices(service = "google")
}

# Coqui TTS
if (tts_auth(service = "coqui")) {
tts_voices(service = "coqui")
}