Text-to-speech via Azure Cognitive Services Speech REST API. Neural voices, SSML support. Auth via apiKey param or AZURE_SPEECH_KEY env var. Region extracted from baseUrl (e.g. https://eastus.tts.speech.microsoft.com) or AZURE_SPEECH_REGION env var.
ttsazurespeechneuralaudiomicrosoft
Input Parameters
Parameter
Type
Description
textrequired
string
Text to convert to speech.
voiceoptional
string
Neural voice name (e.g. en-US-JennyNeural, es-ES-AlvaroNeural). Default: en-US-JennyNeural. Default: en-US-JennyNeural.
modeloptional
string
Unused — Azure selects model via voice name.
outputPathoptional
string
Save audio to this file path (e.g. C:\speech.mp3). Returns base64 audio if empty.