Voice Agent Samples in Foundry Agent Service
Explore Voice Agent in Foundry Agent Service for voice agent guides, portal links, and runnable samples.
Azure Cognitive Service TTS Samples
Microsoft Text to speech service now is officially supported by Speech SDK now. It is recommended way to use TTS in your service or apps. The REST API samples are just provided as referrence when SDK is not supported on the desired platform.
Below are latest updates from Azure TTS. It is updated regularly.
Azure Cognitive Service TTS Customer Story
- AT&T (Media and Entertainment) - AT&T Launches Looney Tunes 5G Experience - YouTube
- Duolingo (Language Learning) - Are you talking to me? Azure AI brings iconic characters to life with Custom Neural Voice - AI for Business (microsoft.com)
- Progressive (Insurance) - Progressive gives voice to Flo’s chatbot, and it’s as no-nonsense and reassuring as she is
- BBC (News Media) - Microsoft Customer Story-BBC innovates how it delivers trusted news and entertainment with Azure AI
- USA today USA TODAY taps into Azure Text-to-Speech to naturally read premium articles aloud
- Le Monde Introducing Audio Articles: A New Service for Subscribers of Le Monde Powered by Microsoft Azure Cognitive Services.
- Wedel software Wedel Software disrupts audio advertising and broadcast radio with Azure AI
- Veritone Microsoft partner Veritone provides a synthetic voice solution featuring Azure AI to save time and reach new audiences
- Laerdal Medical Laerdal Medical Uses Azure AI Text to Speech to Create Immersive Training Experience
- Swisscomm (Telco) - Microsoft Customer Story-Swisscom uses Azure to drive innovation, market leadership with multilingual voice assistant
- Pearson (Education) - Pearson empowers language students to learn faster in a natural way with Azure AI capabilities
- Pearson (Audiobook) - Pearson transforms language learning with Microsoft Azure AI
- Great Wall Moters 长城汽车联合微软科技 共同见证“云上长城”进击全球
- Xpeng Motors (Automotive) - 摊牌了！小P我要变“声”了
- Li Auto (Automotive) - 理想OTA 2.2版本发布，揭秘语音助手底层逻辑
- Kahoot! (Education) - Makes learning more accessible for everyone with Azure Cognitive Services
- Hongdandan (Audiobook) - Chinese nonprofit uses text-to-speech technology to expand access to audiobooks for people who are blind
- NTT Disruption Jibo (Assistant) - NTT Disruption transforms healthcare experiences with social robot jibo and Azure AI
- Berlitz Berlitz empowered 500,000 language learners using Azure AI Speech
- NCMMSC2022: Low resource TTS challenge winners - “面向蒙古语的低资源语音合成竞赛（Mongolian Text-to-Speech Challenge under Low-Resource Scenario
- ICASSP 2023 Lightweight, multispeaker,multilingual TTS challenge winner
- Blizzard Challenge 2021: 1st place Winner in Spanish TTS Challenge
- Blizzard Challenge 2023: 1st place Winner in French audiobook TTS Challenge
Azure Cognitive Service TTS Blog and News
Here lists the Azure Cognitive TTS product blog, customer stories and Microsoft TTS research news etc.
- 2025.03 March 2025: Azure AI Speech’s HD voices are generally available and more
- 2025.02 Azure AI Speech text to speech Feb 2025 updates: New HD voices and more
- 2024.12 Azure AI voices in Arabic improved pronunciation
- 2024.11 Latest updates to the Azure AI Speech Service: video translator API, customized avatar
- 2024.09 New HD voices preview in Azure AI Speech: contextual and realistic output evolved
- 2024.08 Experience the Power of Our Expanded Collection of 60+ Realistic Multilingual Voices
- 2024.07 TTS Avatar GA
- 2024.06 Make your voice chatbots more engaging with new text to speech features
- 2024.05 Announcing Video Translation & Speech Translation API Enhancements
- 2024.05 Create personalized voices with Azure AI Speech
- 2024.04 How OPPO is using Azure AI Speech to bring new innovative Ai features to their phones
- 2024.03 9 More Realistic AI Voices for Conversations Now Generally Available
- 2024.02 Announcing OpenAI text-to-speech voices on Azure OpenAI Service and Azure AI Speech
- 2024.01 Azure AI Speech launches new zero-shot TTS models for Personal Voice
- 2023.12 Introducing more multilingual AI voices optimized for conversations
- 2023.11 Azure AI Speech launches Personal Voice in preview
- 2023.11 Azure AI Speech announces public preview of text to speech avatar
- 2023.10 Project Gutenberg open audiobook is recognized with one of the top 200 best inventions of 2023
- 2023.10 Introducing 7 new realistic AI voices optimized for conversations in 7 languages for public preview
- 2023.09 Introducing super realistic AI voices optimized for conversations
- 2023.08 Introducing new multilingual voices supporting 41 languages and accents with auto language detection
- 2023.07 Project Gutenberg brings free audiobooks to the global community with AI-generated book narration
- 2023.07 Creating a branded AI voice that conveys emotions and speaks multiple languages
- 2023.06 Azure AI Neural TTS enhanced expressiveness for Chinese voices with upgraded prosody breaks
- 2023.05 NaturalSpeech 2:Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers
- 2023.04 Azure Neural TTS Web Player: let your website speak for itself
- 2023.04 HelloTalk: The world's largest language exchange platform empowers language learners with Azure AI
- 2023.03 Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling
- 2023.03 FoundationTTS: Text-to-Speech for ASR Customization with Generative Language Model
- 2023.03 3 Microsoft Azure AI product features that accelerate language learning
- 2023.02 Speech Service Update – Hierarchical Transformer for Pronunciation Assessment
- 2023.01 Low-resource technology updates for Azure Neural Text-to-Speech
- 2023.01 VALLE: Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers
- 2023.01 Azure Neural TTS now available on devices for disconnected and hybrid scenarios
- 2022.12 Azure Custom Neural Voice introduces new emotional styles to support brand voices
- 2022.11 Azure Cognitive Services releases new languages and voices for Neural Text-to-Speech
- 2022.10 Azure Neural TTS voices upgraded to 48kHz with HiFiNet2 vocoder
- 2022.09 Introducing AI-generated voices for Azure neural text to speech service
- 2022.08 3 ways Azure Speech transforms game development with AI
- 2022.08 Microsoft expands global language support for Speech-to-Text & Text-to-Speech
- 2022.07 DelightfulTTS 2: End-to-End Speech Synthesis with Adversarial Vector-Quantized Auto-Encoders
- 2022.07 Azure Neural TTS previews a new contextual voice model for long-form paragraph reading
- 2022.06 11 new languages and variants and more voices are added to Azure’s Neural Text to Speech service
- 2022.06 New technical research is advancing Azure’s Neural Text-to-Speech service
- 2022.05 NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality
- 2022.05 Announcing new voices and emotions to Azure Neural Text to Speech
- 2022.04 Introducing the watermark algorithm for synthetic voice identification
- 2022.03 Try out Custom Neural Voice in 5 minutes with a Lite project
- 2022.02 Azure Cognitive Services releases new languages and voices for Neural Text-to-Speech
- 2022.01 元宇宙离普通人还有多远
- 2022.01 Accelerate the in-vehicle digital experience with Azure Cognitive Services
- 2022.01 XPENG Integrates Text-to-Speech Service From Microsoft in P7 Smart Sedan
- 2021.12 Azure AI milestone: New Neural Text-to-Speech models more closely mirror natural speech
- 2021.12 中国首位超写实虚拟偶像签约华纳，会是流量明星的对手吗？
- 2021.11 How to Create a Custom Neural Voice
- 2021.11 DelightfulTTS: The Microsoft Speech Synthesis System for Blizzard Challenge 2021
- 2021.11 Azure Speech’s Neural TTS empowers organizations to serve users in more than 100 languages
- 2021.10 哈酱的这首“MISS WHO”结合了电子风与国风元素，还加入了部分的昆曲，人声部分采用了微软首个AI语音定制技术 (Microsoft Azure Text-to-Speech Technology)进行创作
- 2021.09 Latest updates on Azure Neural TTS: new voices for casual conversations
- 2021.09 New natural-sounding voices come to Read Aloud
- 2021.08 5 ways Microsoft Edge is better than Chrome, Read Aloud is one of the 5, PCWorld
- 2021.07 Introducing the latest technology advancement in Azure Neural TTS: Uni-TTSv3
- 2021.06 Speech Service Update - Pronunciation Assessment is Generally Available
- 2021.05 Build 2021 – Azure Cognitive Services – Speech Updates
- 2021.04 Enable read-aloud for your application with Azure neural TTS
- 2021.04 FastCompany: 8 great Microsoft Edge features that make switching worth it, read aloud is one of them
- 2021.03 ICLR 2021: AdaSpeech: Adaptive Text to Speech for Custom Voice
- 2021.03 Eleven more languages are generally available for Azure Neural Text-to-Speech
- 2021.02 Are you talking to me? Azure AI brings iconic characters to life with Custom Neural Voice
- 2021.02 Build a natural custom voice for your brand
- 2021.01 Unified Neural Text Analyzer: an innovation to improve Neural TTS pronunciation accuracy
- 2020.12 国际残疾人日：微软正式捐赠首批人工智能有声内容，包括鲁迅、老舍、萧红、朱自清等作家的经典作品
- 2020.12 ICLR 2021: FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
- 2020.12 Azure Neural Text-to-Speech updates: 51 new voices added to the portfolio
- 2020.11 BBC innovates how it delivers trusted news and entertainment with Azure AI
- 2020.11 Neural Text-to-Speech previews five new languages with innovative models in the low-resource setting
- 2020.10 Azure Neural TTS upgraded with HiFiNet, achieving higher audio fidelity and faster synthesis speed
- 2020.09 Swisscom uses Azure Custom Neural Voice to drive innovation, market leadership with multilingual voice assistant
- 2020.09 Ignite 2020 Neural TTS updates: new language support, more voices and flexible deployment options
- 2020.08 Improve remote learning with speech-enabled apps powered by Azure Cognitive Service
- 2020.07 Neural Text to Speech extends support to 15 more languages with state-of-the-art AI quality
- 2020.06 微软上线语音测评服务，赋能语言学习的教和学
- 2020.05 BBC ships voice assistant with custom neural voice
- 2020.05 Neural TTS is extending support to 11 new locales with 15 new voices
- 2020.05 Making the web more accessible and inclusive for all with Microsoft Edge, talking about Edge read aloud
- 2020.04 Finetune neural text-to-speech output with advanced customization features
- 2020.04 Read Aloud in Word on iOS
- 2020.04 看过很多景色，你还没“见过”声音里的世界：周迅语音为你读书
- 2020.04 Blog: Introducing new voice styles in Azure Cognitive Services
- 2020.04 Microsoft Edge is becoming the browser you didn’t know you needed, talking about natural voices | Demo
- 2020.03 Blog: Cognitive Services adds Brazilian Portuguese to Neural Text to Speech
- 2020.03 科技宝藏 | 微软听听文档，AI语音全线升级！
- 2020.02 Versão final da Bixby falando em português é liberada! Vem saber tudo! | Demo
- 2019.12 NeurIPS 2019: FastSpeech: New text-to-speech model improves on speed, accuracy, and controllability
- 2019.11 Blog: Play My Emails in Outlook and get time back in your day | Demo
- 2019.11 Delivering the benefits of Custom Neural Voice
- 2019.11 Azure custom neural voice public preview | Demo
- 2019.10 Microsoft breaks new ground with AI neural TTS and life-size holograms | Demo
- 2019.10 微软“晓晓”让温暖的声音浸润心目图书馆 | AI for Good
- 2019.09 让电脑说人话 | 数字化转型 ING
- 2019.08 Blog: Bringing cloud powered voices to Microsoft Edge Insiders
- 2019.06 Blog: Inclusive Classroom round up for Microsoft Education at ISTE 2019
- 2019.05 Blog: Azure Neural text-to-speech generally available
- 2019.05 ICML 2019 | 微软提出极低资源下语音合成与识别新方法，小语种也不怕没数据了
- 2019.03 Microsoft Word reads to you: How to use the Speak and Read Aloud commands
- 2019.03 Blog: Bing delivers text-to-speech and greater coverage of intelligent answers and visual search | Demo
- 2019.02 王源版小米小爱语音，微软Azure是背后功臣 | Demo
- 2019.01 AAAI 2019: Neural Speech Synthesis with Transformer Network
- 2018.12 Blog: Microsoft previews neural network text-to-speech
- 2018.09 Blog: Microsoft’s new neural text-to-speech service helps machines speak like people
Azure Cognitive Service TTS Links
- Azure Speech Document
- Create Custom Neural Voice
- Speech SDK
- Azure Speech Containers
- Language support - Speech service - Azure Cognitive Services | Microsoft Docs
- Speech Synthesis Markup Language (SSML) - Speech service - Azure Cognitive Services | Microsoft Docs
- Speech Studio - Microsoft Azure
- Text-to-speech quickstart - Speech service - Azure Cognitive Services | Microsoft Docs
- Cognitive Speech Services Pricing | Microsoft Azure
- Guidelines for responsible deployment of synthetic voice technology - Azure Cognitive Services | Microsoft Docs
- Disclosure for voice talent | Microsoft Docs
- Disclosure Design Guidelines - Azure Cognitive Services | Microsoft Docs
- Latency, load testing of Azure TTS
- Azure TTS wiki
- Pricing Note: how billing character is calculated
Contributing
We welcome contributions. Feel free to file issues and pull requests on the repo and we'll address them as we can. Learn more about how you can help on our Contribution Rules & Guidelines.
You can reach out to us anytime with questions and suggestions using our communities below:
- Support questions: StackOverflow
- Feedback & feature requests: Cognitive Services UserVoice Forum
This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact [email protected] with any additional questions or comments.
License
All Microsoft Cognitive Services SDKs and samples are licensed with the MIT License. For more details, see LICENSE.
Sample images are licensed separately, please refer to LICENSE-IMAGE.
Developer Code of Conduct
Developers using Cognitive Services, including this client library & sample, are expected to follow the “Developer Code of Conduct for Microsoft Cognitive Services”, found at http://go.microsoft.com/fwlink/?LinkId=698895.