ms_synthesize: Get Microsoft Text To Speech (TTS) or Cognitive Services...

In muschellij2/mscstts: R Client for the Microsoft Cognitive Services 'Text-to-Speech' REST API

Get Microsoft Text To Speech (TTS) or Cognitive Services Token from API Key

Description

Get Microsoft Text To Speech (TTS) or Cognitive Services Token from API Key

Usage

ms_synthesize(
  script,
  token = NULL,
  api_key = NULL,
  gender = c("Female", "Male"),
  language = "en-US",
  voice = NULL,
  output_format = c("raw-16khz-16bit-mono-pcm", "raw-8khz-8bit-mono-mulaw",
    "riff-8khz-8bit-mono-alaw", "riff-8khz-8bit-mono-mulaw", "riff-16khz-16bit-mono-pcm",
    "audio-16khz-128kbitrate-mono-mp3", "audio-16khz-64kbitrate-mono-mp3",
    "audio-16khz-32kbitrate-mono-mp3", "raw-24khz-16bit-mono-pcm",
    "riff-24khz-16bit-mono-pcm", "audio-24khz-160kbitrate-mono-mp3",
    "audio-24khz-96kbitrate-mono-mp3", "audio-24khz-48kbitrate-mono-mp3"),
  escape = FALSE,
  region = NULL,
  api = c("tts", "bing"),
  ...
)

ms_region(region = ms_regions())

ms_regions()

ms_set_region(region = ms_regions())

ms_synthesize_api_url(api = c("tts", "bing"), region = NULL)

Arguments

script	A character vector of lines to be spoken
token	An authentication token, base-64 encoded usually from ms_get_tts_token. If not provided, will be created from ms_get_tts_token
api_key	Microsoft Cognitive Services API key, if token is not provided.
gender	Sex of the Speaker
language	Language to be spoken, must be from ms_language_codes
voice	full voice name, usually from ms_language_to_ms_name. Will override language and gender.
output_format	Format of the output, see https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/how-to-migrate-from-bing-speech for more information
escape	Should non-standard characters be substituted? Should not be used if script has SSML tags. See ms_create_ssml
region	Subscription region for your key. See https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/overview#reference-docs
api	which API to authorize on, either tts for text to speech or bing for Bing text to speech API
...	Additional arguments to send to POST

Value

A list of the request, content, token, and 'SSML'.

Note

The content is likely in a binary format and the output depends on the 'output_format' chosen. For example, if the 'output_format' is an 'MP3', then see below example

Examples

## Not run: 
if (ms_have_tts_key()) {
res = ms_synthesize(
script = "hey, how are you doing? I'm doing pretty good",
output_format = "audio-16khz-128kbitrate-mono-mp3")
tmp <- tempfile(fileext = ".mp3")
writeBin(res$content, con = tmp)
mp3 = tuneR::readMP3(tmp)
}


## End(Not run)
ms_regions()

muschellij2/mscstts documentation built on June 17, 2022, 10:29 a.m.