Microsoft Azure Text to Speech

E743717

Microsoft Azure Text to Speech is a cloud-based service from Microsoft that converts written text into natural-sounding spoken audio using advanced neural speech synthesis.

Jump to: Statements Referenced by

Statements (48)

Predicate Object
instanceOf Microsoft Azure Cognitive Service
speech synthesis service
authenticationMethod API key
Azure Active Directory NERFINISHED
availableAs Azure resource NERFINISHED
deploymentModel cloud
developer Microsoft
hasCapability batch speech synthesis
convert text to spoken audio
custom voice creation
neural text-to-speech synthesis
real-time speech synthesis
speech synthesis markup language support
partOf Azure Cognitive Services NERFINISHED
Microsoft Azure NERFINISHED
pricingModel consumption-based
requires Azure subscription
supportsFeature audio format selection
long-form text synthesis
neural voices
prosody control
sample rate configuration
speech synthesis in multiple languages
speech synthesis in multiple locales
standard voices
streaming audio output
style and emotion control
voice cloning with consent
voice tuning
supportsProtocol REST API
WebSocket NERFINISHED
supportsSDK .NET NERFINISHED
C++
Java NERFINISHED
JavaScript NERFINISHED
Python NERFINISHED
supportsStandard SSML
typicalUseCase IVR systems
accessibility applications
audiobook generation
content narration
customer service bots
voice assistants
usesTechnology artificial intelligence
deep neural networks
machine learning
neural speech synthesis
website https://azure.microsoft.com/services/cognitive-services/text-to-speech/

Referenced by (1)

Full triples — surface form annotated when it differs from this entity's canonical label.

Google Cloud Text-to-Speech competesWith Microsoft Azure Text to Speech