PowerShell script to use Azure Speech Service TTS

AzureTTS.ps1

#
# PowerShell script to use Azure Speech Service TTS and play given string argument as a soundfile directly
#
# Author:      https://github.com/dichternebel
# Docs:        https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/rest-text-to-speech?tabs=nonstreaming#convert-text-to-speech
# Test voices: https://azure.microsoft.com/en-us/products/cognitive-services/text-to-speech/#overview

# Prepare
$subscriptionKey = 'YourVerySecretKeyGoesHere' # paste your Azure Speech key here
$azureRegion = 'westeurope' # Change this to match the region of your Azure Speech service
$voice = 'de-DE-AmalaNeural' # https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/language-support?tabs=stt-tts
$tempo = '20%' # increases/decreases the tempo by given percentage
$pitch = '-10%' # pitches the voice by given percentage
#
# no need to change things below this line!
#

# Get text taking the first argument, you need to use quotes to pass sentences.
$Content = $args[0]
if ([string]::IsNullOrEmpty($Content)) {
  # Tell user being a noob by not giving an argument to the script
  $voice = 'de-DE-GiselaNeural'
  $tempo = '10%'
  $pitch = '0%'
  $Content = 'Los gib Argument, du Kacknuub und mach mal was Geiles, Digger!'
}

# Auth
$FetchTokenHeader = @{
  'Content-type' = 'application/x-www-form-urlencoded';
  'Content-Length' = '0';
  'Ocp-Apim-Subscription-Key' = $subscriptionKey
}
$OAuthToken = Invoke-RestMethod -Method POST -Uri https://$azureRegion.api.cognitive.microsoft.com/sts/v1.0/issuetoken -Headers $FetchTokenHeader

# https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/rest-text-to-speech?tabs=nonstreaming#audio-outputs
$AudioOutputType='riff-48khz-16bit-mono-pcm' 

# Prepare REST call
$Uri = "https://$azureRegion.tts.speech.microsoft.com/cognitiveservices/v1"

$Headers = @{
  'X-Microsoft-OutputFormat' = $AudioOutputType;
  'User-Agent' = 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:15.0) Gecko/20100101 Firefox/15.0.1';
  'Authorization' = "Bearer: $OAuthToken";
  'Host' = "$azureRegion.tts.speech.microsoft.com"
  }

$Body = @"
<speak xmlns="http://www.w3.org/2001/10/synthesis" xmlns:mstts="http://www.w3.org/2001/mstts" xmlns:emo="http://www.w3.org/2009/10/emotionml" version="1.0" xml:lang="en-US">
  <voice name="$voice">
    <prosody rate="$tempo" pitch="$pitch">
      $Content
    </prosody>
  </voice>
</speak>
"@

# Prepare output file
$timestamp = Get-Date -Format FileDateTime
$FilePath = "$PSScriptRoot/output_$timestamp.wav"

# Post payload and get WAV file
# Hint: If you do not set the ContentType here, then e.g. umlauts will not work!
Invoke-RestMethod -Uri $Uri -Method POST -Headers $Headers -ContentType 'application/ssml+xml; charset=utf-8' -Body $Body -OutFile $FilePath

# Play it
$Soundplayer=New-object System.Media.Soundplayer
$Soundplayer.SoundLocation = $FilePath
$Soundplayer.playsync()

# Clean up the mess
Remove-Item $FilePath