Azure Speech in Foundry Tools
Energize your apps and agents with prebuilt, customizable, multilingual speech AI models.
OVERVIEW
Discover the latest Azure Speech capabilities
- Build voice-enabled, multilingual generative AI apps with fast transcriptions and natural-sounding voices.
- Enable AI agents with end-to-end speech, including customized transcription, voice, and avatars.
- Enable real-time, multi-language speech-to-speech translation and speech-to-text transcription of audio streams.
- Run AI models wherever your data resides. Deploy your apps in the cloud or at the edge with containers.
USE CASES
Develop multimodal generative AI apps with speech models
Build voice-enabled agents
Use foundation models along with customized audio-in and audio-out models to power agents with voice.
Transcribe speech to text
Transcribe call center or meeting conversations. Go global with audio captioning in more than 100 languages.
Convert text to speech
Build bots that speak naturally. Differentiate your brand with customized, realistic voices and speaking styles.
Use post-call analytics
Analyze audio or video call recordings to gain deep insights using foundation models in Azure Content Understanding in Foundry Tools.
Transcribe audio with OpenAI Whisper
Transform your call centers using the latest OpenAI Whisper model in Azure Speech or Azure OpenAI in Foundry Models.
Build your avatars
Bring your brand to life using prebuilt or custom avatars with natural-sounding voices.
Enable multilingual communication
Translate audio or video data from and into an ever-growing list of supported languages. Customize translations to your industry.
Embed speech
Use embedded speech to power on-device speech-to-text and text-to-speech scenarios where cloud connectivity is intermittent or unavailable.
Security
Embedded security and compliance
>100
Compliance certifications, including over 50 specific to global regions and countries.
Pricing
Flexible pricing to meet your needs
Pay for only what you use—no upfront costs. Azure Speech pay-as-you-go pricing is based on:
- The number of hours of audio you transcribe or translate for speech to text and speech translation.
- The number of characters you convert to audio for text to speech.
- The number of transactions for speaker recognition.
RELATED PRODUCTS
Azure products work better together
Build comprehensive solutions using Azure Speech and other Azure AI products.
Azure OpenAI
Incorporate multimodality and enhance apps with models that combine multiple types of data, such as text, images, video, and audio.
Microsoft Foundry
Get everything you need to develop generative AI applications and custom agents on one platform.
Content Safety in Foundry Control Plane
Deliver secure and trustworthy solutions with built-in tools that put responsible AI principles into practice.
Azure Content Understanding
Accelerate the transformation of multimodal data into insights.
Azure Translator
Translate documents and text in real-time or in batches across more than 100 languages for global reach.
Azure Language
Build conversational interfaces, summarize documents, and analyze text using prebuilt AI-powered features.
CUSTOMER STORIES
See what customers are building with Azure Speech
Fortune Brands Innovations unifies their brands under one portal with Microsoft Power Pages
Fortune Brands Innovations created a more streamlined customer experience using Microsoft Power Pages and Dynamics 365 Customer Experience.
Solv eliminates 98% of clerical errors with Dynamics 365 Business Central
Solv improved report accuracy and efficiency by switching to Dynamics 365 Business Central, saving 40 man-hours monthly and enhancing financial controls.
Syensqo.AI leverages Azure OpenAI Service to develop SyGPT chatbot in record time
Syensqo.AI, a division of the Belgian science and technology leader Syensqo, has developed SyGPT, an advanced AI chatbot using Azure OpenAI Service.
RESOURCES
Get started with Azure Speech
Explore Azure Speech documentation
Discover resources such as tutorials and API references.
Build voice-enabled apps
Design and build enterprise-grade, voice-enabled apps.
GitHub resources
Explore sample code and SDKs.
Start building now
Build models quickly in Foundry.
Azure Speech learning paths
Develop natural language processing solutions with Azure.
Create agentic AI
Integrate AI agents into apps seamlessly and learn advanced model fine-tuning techniques.
Find the best AI model
Enable multimodal models, model selection, and benchmarking, and create multimodal applications.
Secure and responsible AI
Understand the fundamentals of AI security, evaluations, and managing harmful content.
FAQ
Frequently asked questions
- Azure Speech is part of Foundry Tools (formerly Azure AI Services) and provides APIs for speech-to-text, text-to-speech, translation, and speaker recognition. It was previously known as Azure AI Speech.
Yes, we’re rebranding many of our former Azure AI Services as Foundry Tools. This shift reflects a broader platform unification under Foundry, and signals that these services are now positioned as core tools for building agentic AI applications.
Azure Speech in Foundry Tools still offers the same powerful capabilities—like speech recognition, text-to-speech, and translation—but is now part of a cohesive toolkit designed for developers building intelligent agents.
The rebrand helps clarify how these APIs fit into the Foundry ecosystem and makes it easier to discover, orchestrate, and integrate them into modern AI workflows.- Azure Speech offers a number of features and capabilities, including speech to text, text to speech, and speech translation. These are offered through SDKs in several programming languages, including C#, C++, and Java.
- Speech supports an ever-growing set of languages. For supported languages, please refer tothe current list.
- Customers are building interesting applications using Foundry Tools. Get started with Azure Speech for use cases including conversational AI, post-call analytics, and video summarization.
Next steps
Choose the Azure account that’s right for you
Pay as you go or try Azure free for up to 30 days.
AI development tools
Design and manage AI applications
Create, customize, and scale AI apps and agents efficiently.
Business Solutions Hub
Drive results with innovative cloud solutions
Browse the Business Solutions Hub to find products and solutions to achieve your goals.
