Example of connecting Windows PowerShell to the Azure Cognitive Text to Speech API

powershell/AzureTTS-RestAPI-PowerShell.ps1

@@ -0,0 +1,100 @@
+Function Play-MediaFile($Filename)
+{
+# PowerShell Function to play WAV file programatically without invoking Media Player
+# Supplied file must be a standard Windows WAV
+
+# Note, function has no error checking
+$PlayMedia=New-object System.Media.Soundplayer
+$PlayMedia.SoundLocation=($Filename)
+$PlayMedia.playsync()
+}
+
+# Generate Access token to allow use of Cognitive Text to Speech API
+# and store in $AccessToken
+
+$Uri="https://api.cognitive.microsoft.com/sts/v1.0/issueToken"
+$Method="POST"
+$ContentType="application/json"
+$APIKey='-----' 
+$Headers=@{'Ocp-Apim-Subscription-Key' = $APIKey }
+
+# Call up Access Token API with Provided Subscription Key
+$AccessToken=Invoke-RestMethod -Uri $URI `
+-Method $METHOD -ContentType $ContentType `
+–Headers $HEADERS
+
+# Define Headers for REST API
+# Type of Audio File
+$AudioOutputType='riff-16khz-16bit-mono-pcm' 
+
+# SearchAppID Guid - Generate using (New-Guid).guid | Set-Clipboard and "Paste" in section between ''
+$XSearchAppId=''
+
+# SearchClientID Guid - Generate using (New-Guid).guid | Set-Clipboard and "Paste" in section between ''
+
+$XSearchClientId=''
+
+# Name of Calling application
+$UserAgent='SampleApplicationName'
+
+# Populate the header values
+$Headers=@{ `
+'Content-Type' = 'application/ssml+xml'; `
+'X-Microsoft-OutputFormat' = $AudioOutputType; `
+'X-Search-AppId' = $XSearchAppId; `
+'X-Search-ClientId' = $XSearchClientId; `
+'Authorization' = $AccessToken `
+}
+
+$Uri= 'https://speech.platform.bing.com/synthesize'
+$Method='POST'
+$ContentType='application/ssml+xml'
+$Filename='output.wav'
+
+#$Headers=@{'Content-Type' = 'application/ssml+xml';'X-Microsoft-OutputFormat' = $AudioOutputType;'X-Search-AppId' = $XSearchAppId; 'X-Search-ClientId' = $XSearchClientId; 'Authorization' = $AccessToken }
+#^^^ ^^^ ^^^
+# Or does THIS make more sense to you for the header?
+
+# Define the Region for the Voice (You will note there *is* a unique region for each voice
+# as the Spanish voice region (es-ES) will pronounce Spanish words far better than the
+# English voice (en-US) as it is TUNED to that language.   But you CAN mix if you're interested
+
+$Region='en-US'
+$Voice='"Microsoft Server Speech Text to Speech Voice (en-US, JessaRUS)"'
+$Content="It's time for a little PowerShell fun"
+
+$Body='<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xmlns:mstts="http://www.w3.org/2001/mstts" xml:lang="'+$region+'"><voice xml:lang="' +$Region+'" name='+$Voice+'>'+$Content+'</voice></speak>'
+
+Invoke-RestMethod -Uri $Uri -Method $Method `
+-Headers $Headers -ContentType $ContentType `
+-Body $Body -UserAgent $UserAgent `
+-OutFile $Filename
+Play-MediaFile -Filename $Filename
+break
+
+# Body in Spanish
+$Region='es-ES'
+$Voice='"Microsoft Server Speech Text to Speech Voice (es-ES, Pablo, Apollo)"'
+$Content="Es hora de un poco de diversión PowerShell"
+
+$Body='<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xmlns:mstts="http://www.w3.org/2001/mstts" xml:lang="'+$region+'"><voice xml:lang="' +$Region+'" name='+$Voice+'>'+$Content+'</voice></speak>'
+
+Invoke-RestMethod -Uri $Uri -Method $Method `
+-Headers $Headers -ContentType $ContentType `
+-Body $Body -UserAgent $UserAgent `
+-OutFile $Filename
+Play-MediaFile -Filename $Filename
+break
+
+# Body in French
+$Region='fr-FR'
+$Voice='"Microsoft Server Speech Text to Speech Voice (fr-FR, HortenseRUS)"'
+$Content="Il est temps pour un peu de fun PowerShell"
+
+$Body='<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xmlns:mstts="http://www.w3.org/2001/mstts" xml:lang="'+$region+'"><voice xml:lang="' +$Region+'" name='+$Voice+'>'+$Content+'</voice></speak>'
+
+Invoke-RestMethod -Uri $Uri -Method $Method `
+-Headers $Headers -ContentType $ContentType `
+-Body $Body -UserAgent $UserAgent `
+-OutFile $Filename
+Play-MediaFile -Filename $Filename

powershell/PowerShell-TTS-RestApi-Sample.PS1

@@ -0,0 +1,100 @@
+Function Play-MediaFile($Filename)
+{
+# PowerShell Function to play WAV file programatically without invoking Media Player
+# Supplied file must be a standard Windows WAV
+
+# Note, function has no error checking
+$PlayMedia=New-object System.Media.Soundplayer
+$PlayMedia.SoundLocation=($Filename)
+$PlayMedia.playsync()
+}
+
+# Generate Access token to allow use of Cognitive Text to Speech API
+# and store in $AccessToken
+
+$Uri="https://api.cognitive.microsoft.com/sts/v1.0/issueToken"
+$Method="POST"
+$ContentType="application/json"
+$APIKey='-----' 
+$Headers=@{'Ocp-Apim-Subscription-Key' = $APIKey }
+
+# Call up Access Token API with Provided Subscription Key
+$AccessToken=Invoke-RestMethod -Uri $URI `
+-Method $METHOD -ContentType $ContentType `
+–Headers $HEADERS
+
+# Define Headers for REST API
+# Type of Audio File
+$AudioOutputType='riff-16khz-16bit-mono-pcm' 
+
+# SearchAppID Guid - Generate using (New-Guid).guid | Set-Clipboard and "Paste" in section between ''
+$XSearchAppId=''
+
+# SearchClientID Guid - Generate using (New-Guid).guid | Set-Clipboard and "Paste" in section between ''
+
+$XSearchClientId=''
+
+# Name of Calling application
+$UserAgent='SampleApplicationName'
+
+# Populate the header values
+$Headers=@{ `
+'Content-Type' = 'application/ssml+xml'; `
+'X-Microsoft-OutputFormat' = $AudioOutputType; `
+'X-Search-AppId' = $XSearchAppId; `
+'X-Search-ClientId' = $XSearchClientId; `
+'Authorization' = $AccessToken `
+}
+
+$Uri= 'https://speech.platform.bing.com/synthesize'
+$Method='POST'
+$ContentType='application/ssml+xml'
+$Filename='output.wav'
+
+#$Headers=@{'Content-Type' = 'application/ssml+xml';'X-Microsoft-OutputFormat' = $AudioOutputType;'X-Search-AppId' = $XSearchAppId; 'X-Search-ClientId' = $XSearchClientId; 'Authorization' = $AccessToken }
+#^^^ ^^^ ^^^
+# Or does THIS make more sense to you for the header?
+
+# Define the Region for the Voice (You will note there *is* a unique region for each voice
+# as the Spanish voice region (es-ES) will pronounce Spanish words far better than the
+# English voice (en-US) as it is TUNED to that language.   But you CAN mix if you're interested
+
+$Region='en-US'
+$Voice='"Microsoft Server Speech Text to Speech Voice (en-US, JessaRUS)"'
+$Content="It's time for a little PowerShell fun"
+
+$Body='<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xmlns:mstts="http://www.w3.org/2001/mstts" xml:lang="'+$region+'"><voice xml:lang="' +$Region+'" name='+$Voice+'>'+$Content+'</voice></speak>'
+
+Invoke-RestMethod -Uri $Uri -Method $Method `
+-Headers $Headers -ContentType $ContentType `
+-Body $Body -UserAgent $UserAgent `
+-OutFile $Filename
+Play-MediaFile -Filename $Filename
+break
+
+# Body in Spanish
+$Region='es-ES'
+$Voice='"Microsoft Server Speech Text to Speech Voice (es-ES, Pablo, Apollo)"'
+$Content="Es hora de un poco de diversión PowerShell"
+
+$Body='<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xmlns:mstts="http://www.w3.org/2001/mstts" xml:lang="'+$region+'"><voice xml:lang="' +$Region+'" name='+$Voice+'>'+$Content+'</voice></speak>'
+
+Invoke-RestMethod -Uri $Uri -Method $Method `
+-Headers $Headers -ContentType $ContentType `
+-Body $Body -UserAgent $UserAgent `
+-OutFile $Filename
+Play-MediaFile -Filename $Filename
+break
+
+# Body in French
+$Region='fr-FR'
+$Voice='"Microsoft Server Speech Text to Speech Voice (fr-FR, HortenseRUS)"'
+$Content="Il est temps pour un peu de fun PowerShell"
+
+$Body='<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xmlns:mstts="http://www.w3.org/2001/mstts" xml:lang="'+$region+'"><voice xml:lang="' +$Region+'" name='+$Voice+'>'+$Content+'</voice></speak>'
+
+Invoke-RestMethod -Uri $Uri -Method $Method `
+-Headers $Headers -ContentType $ContentType `
+-Body $Body -UserAgent $UserAgent `
+-OutFile $Filename
+Play-MediaFile -Filename $Filename