Azure-Speech-Text-to-speech

Version: 1

Microsoft•Last updated December 2025

Text-to-speech enables your applications, tools, or devices to convert text into natural synthesized speech. It leverages advanced out-of-the-box [prebuilt neural voices](https://learn.microsoft.com/en-us/azure/ai-services/speech-service/language-support?t

Azure Speech

Azure Speech is a comprehensive suite of AI-powered speech capabilities that includes speech to text, text to speech, speech translation, and voice live AI. It enables developers to build intelligent voice-enabled applications with high accuracy, multilingual support, and customizable voice experiences.

Key capabilities

About this model

Azure text to speech (TTS) is a neural speech synthesis model designed to convert written text into highly natural speech. It excels in delivering expressive and context-aware audio output using prebuilt neural voices or custom voice models tailored to specific brands or applications. This model is particularly valuable for developers building applications that require lifelike voice interaction, such as virtual assistants, accessibility tools, customer service bots, and content narration. With support for SSML-based fine-tuning, multilingual capabilities, and batch synthesis for long-form audio, Azure TTS offers flexibility, scalability, and high-quality voice generation across diverse use cases.

Key model capabilities

Azure Text-to-Speech offers several core capabilities that make it a powerful tool for developers building voice-enabled applications:

Neural Voice Synthesis
Delivers highly natural and expressive speech using advanced deep learning models. Neural voices replicate human intonation, rhythm, and emotion, enhancing user engagement across conversational interfaces.
Custom Neural Voice
Enables creation of unique, brand-specific voices through voice talent recordings and model training. This allows organizations to deliver consistent and personalized audio experiences across platforms.
SSML-Based Speech Tuning
Supports Speech Synthesis Markup Language (SSML) for fine-grained control over speech output, including pitch, rate, volume, pronunciation, pauses, etc.
Multilingual and Regional Voice Support
Offers over 150+ languages and variants with multiple voice options per locale, making it ideal for global applications and inclusive user experiences.

Each capability is designed to help developers create high-quality, natural, and scalable voice interactions experience for a wide range of use cases - from accessibility, virtual assistants to media narration and customer service automation.

Use cases

Text to speech offers a variety of features catering to a wide range of intended uses across industries and domains. All text to speech features including video translation are subject to the terms and conditions applicable to customers’ Azure subscription, including the Azure Acceptable Use Policy and the Code of conduct for Azure AI Speech text to speech.

Key use cases

Azure Text-to-Speech enables a wide range of practical applications across industries and domains. Below are key use cases where the model excels:

Educational and Interactive Learning - Create fictional brand or character voices for reading or narrating educational materials, online courses, interactive lesson plans, simulation-based learning, or guided museum tours.
Media: Entertainment - Generate expressive voices for video games, movies, TV shows, recorded music, podcasts, audiobooks, and immersive experiences in augmented or virtual reality.
Media: Marketing and Advertising - Develop branded voices for product introductions, promotional campaigns, business presentations, and advertisements to enhance audience engagement and brand recognition.
Self-authored Content - Enable voice talent to narrate their own written content, such as blogs, books, or personal stories, using custom neural voices.
Accessibility Features - Support audio description systems and narration for visually impaired users, or facilitate communication for individuals with speech impairments using personalized or fictional voices.
Interactive Voice Response (IVR) Systems - Create dynamic and branded voices for call center operations, telephony systems, and automated phone interactions.
Public Service and Informational Announcements - Deliver clear and engaging voice messages for public venues, traffic updates, weather alerts, event information, and schedules. (Note: Not intended for journalistic or news content.)
Translation and Localization - Use multilingual voice synthesis to translate conversations or audio content across different languages, enhancing global accessibility.
Virtual Assistants and Chatbots - Power smart assistants and conversational agents in web platforms, appliances, vehicles, toys, IoT devices, and customer service scenarios with expressive, branded voices.
``

Out of scope use cases

Usage will be restricted to use the service in any way that is inconsistent with the Code of Conduct

Pricing

Picing for Azure text to speech is based on several factors including voice type (standard neural vs custom voice), additional activities like model training or hosting. Developers typically incur costs per million characters or training hours.

Technical specs

Azure Speech's text to speech functionality is part of the Azure AI Speech Service. It uses deep neural networks to generate highly natural speech (commonly referred to as “Neural voices”) with clear articulation and expressive prosody. The service supports real-time and batch synthesis via SDK or REST API, and includes custom voice capabilities for creating branded / customize neural voices.

Training cut-off date

This information is not available.

Input formats

Plain text or Speech Synthesis Markup Language (SSML) , which supports detailed speech control (e.g., pitch, rate, pronunciation, pauses, visemes).

Supported language

Supports 150+ languages and variants, with multiple voice options per locale. Full voice list .

Supported Azure regions

Available in all major Azure regions worldwide.

Sample JSON response

Endpoint	Request Type	Response Format
`GET /voices/list`	None	JSON: voice metadata
`POST /cognitiveservices/v1`	SSML + headers	Binary audio file (MP3 / WAV / Opus / etc.)
Speech SDK `SpeakTextAsync`	Text or SSML	SDK stream + result metadata
Batch synthesis API	Long-form SSML/Text	Asynchronous job → downloadable audio file

Model architecture

This information is not available.

Long context

Azure Speech supports extended context lengths through its Batch synthesis API , which is designed for asynchronous processing of long-form content. This enables tasks such as generating audio for:

Audiobooks
Lectures
Podcasts
Training materials
Long-form narration

Unlike real-time synthesis via the Speech SDK or REST API, batch synthesis handles texts longer than 10 minutes by queuing the request and returning the audio once processing is complete. Developers submit synthesis jobs asynchronously, poll for completion status, and download the final audio when it's ready.

Optimizing model performance

To achieve the best performance with Azure TTS, consider implementing the following optimization strategies:

Additional assets

This information is not available.

Distribution

Azure Text-to-Speech is available through multiple distribution methods to support a wide range of integration scenarios:

Speech SDK
Integrate TTS capabilities directly into applications using Azure’s Speech SDK, available for platforms including .NET, Python, Java, JavaScript, and C++.
REST API
Access TTS functionality via a public, subscription-based API for flexible integration into web services, mobile apps, and backend systems.
Embedded Speech & Containers
Deploy speech models on-premises or at the edge using Azure Speech containers for offline or low-latency environments.

See Azure Speech pricing details for more information.

More information

Learn more in the full Azure AI Speech Service documentation .

Responsible AI considerations

Safety techniques

This information is not available.

Safety evaluations

This information is not available.

Known limitations

Azure Text-to-Speech is designed with responsible AI principles in mind, but developers should be aware of the following limitations and risks:

Linguistic Limitations
While the service supports over 150 languages and variants, voice quality and availability may vary across languages. Some languages may have fewer voice options or less expressive capabilities.
Context and Emotion
The model may struggle to accurately convey nuanced emotions or context-specific intonation, especially in complex or sensitive scenarios. SSML and custom voice tuning can help mitigate this.
Fairness and Representation
Voice datasets may reflect biases in gender, accent, age, or regional representation. Developers should evaluate voice selection carefully to ensure inclusive and equitable user experiences.
Misuse Risks
Synthetic voices can be misused for impersonation, misinformation, or deceptive content. Developers should implement safeguards, such as watermarking, consent management, and usage monitoring.
Reliability in High-Stakes Use Cases
For applications involving healthcare, legal, or emergency communication, Azure TTS should be used with caution and supplemented by human oversight.

Refer to Technical limitations, operational factors, and ranges for more details.

Acceptable use

Acceptable use policy

Approved use cases for Azure text to speech include:

Educational or Interactive Learning
For reading or speaking educational materials, online learning, interactive lesson plans, simulation learning, or guided museum tours.
Media: Marketing or Entertainment
For product introductions, business promotion, advertisements, or speaking entertainment content such as video games, movies, TV, recorded music, podcasts, audiobooks, or AR/VR experiences.
Accessibility Features
For audio description systems, narration, and communication support for individuals with speech impairments.
Interactive Voice Response (IVR) Systems
For call center operations, telephony systems, and automated phone interactions.
Public Service and Informational Announcements
For communicating public service information in venues or broadcasts (e.g., traffic, weather, events). Not intended for journalistic or news content.
Translation and Localization
For translating conversations or audio media across different languages.
Virtual Assistant or Chatbot
For smart assistants, web-based virtual agents, appliances, vehicles, toys, IoT device control, and customer service scenarios.

Refer to use cases for more details.

Terms of Service

Terms of Service Link

Azure Speech - Text to speech is provided under Microsoft’s proprietary licensing terms. Access to the model is subscription-based and governed by Microsoft’s product licensing policies.

License Type: Proprietary
Access Model: Subscription-based via Azure services
Terms of Service: https://microsoft.com/licensing/terms/

Model Specifications

Last UpdatedDecember 2025

Input TypeText

Output TypeAudio

ProviderMicrosoft

Quick Start