Azure Speech in Foundry Tools (formerly Azure AI Speech) is a Microsoft Azure service that gives developers prebuilt, customizable, multilingual speech AI models. It provides APIs and SDKs for speech-to-text, text-to-speech, speech translation, and speaker recognition, with SDKs in several programming languages including C#, C++, and Java. Teams use it to build conversational AI, post-call analytics, video summarization, and voice-first agents, and it is positioned as part of the Foundry toolkit for agentic AI applications. Access is through an Azure account with pay-as-you-go consumption or a free Azure trial of up to 30 days.
How to use Azure Speech
1
Create an Azure account
Sign up for an Azure account with pay-as-you-go billing or start the free Azure trial of up to 30 days.
2
Create a Speech resource
Provision an Azure Speech resource in the Azure portal or through Microsoft Foundry to obtain access for your application.
3
Integrate an SDK or API
Use the speech-to-text, text-to-speech, translation, or speaker recognition APIs through SDKs such as C#, C++, or Java.
Part of Foundry Tools for building agentic AI applications
Azure Speech Use Cases
Conversational AI experiences
Post-call analytics
Video summarization
Voice-first agents in Microsoft Foundry
Azure Speech FAQs
It is the Microsoft Azure service, formerly called Azure AI Speech, that provides APIs for speech-to-text, text-to-speech, translation, and speaker recognition.
No. The service still offers the same capabilities, such as speech recognition, text-to-speech, and translation, but is now positioned within the Foundry toolkit.
It supports speech to text, text to speech, and speech translation, offered through SDKs in several programming languages including C#, C++, and Java.
The documented SDKs include C#, C++, and Java.
It is billed through Azure consumption-based pricing, where you pay only for the resources you use; per-unit rates are listed on the Speech Services pricing page.
Yes. You can start with an Azure account using pay-as-you-go billing or try Azure free for up to 30 days.
Documented examples include conversational AI, post-call analytics, video summarization, and voice-first agents built in Microsoft Foundry.
Speech supports an ever-growing set of languages; the current list is linked from the official Azure Speech page.
Azure Speech is billed through Azure consumption-based pricing; a free Azure trial of up to 30 days is available. Specific per-unit rates are listed on the Speech Services pricing page.
Pay as you go
USD
Consumption-based Azure billing where you pay only for the cloud resources you use and scale as you grow.
Pay only for resources consumed
Scale usage as needed
Access to speech-to-text, text-to-speech, translation, and speaker recognition APIs
Azure free trial
USD / up to 30 days
A time-limited free Azure trial for evaluating services before moving to paid consumption.