ms_synthesize {conrad}

Convert Text to Speech

Description

Convert text to speech by using Speech Synthesis Markup Language (SSML)

Usage

ms_synthesize(
  script,
  region = "westus",
  api_key = NULL,
  token = NULL,
  gender = c("Female", "Male"),
  language = "en-US",
  voice = NULL,
  escape = FALSE
)

Arguments

script

A character vector of text to be converted to speech

region

Subscription region for API key. For more info, see https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/regions

api_key

Microsoft Azure Cognitive Services API key

token

An authentication token

gender

Sex of the speaker

language

Language to be spoken

voice

Full voice name

escape

Should non-standard characters be substituted?

Details

For more info, see Section Convert text to speech of the Microsoft documentation.

Value

An HTTP response in hexadecimal representation of binary data

Examples

# Convert text to speech
res <- ms_synthesize(script = "Hello world, this is a talking computer testing test",
                     region = "westus",
                     gender = "Female")
# Returns hexadecimal representation of binary data

# Create temporary file to store audio output
output_path <- tempfile(fileext = ".wav")
# Write binary data to output path
writeBin(res, con = output_path)
# Play audio in browser
# play_audio(audio = output_path)

# Delete temporary file
file.remove(output_path)