Skip to main content
This is lesson 5 of 9 in this module Course 74% complete
Prev Next Skip

Using Azure Speech APIs

Premium Content

Sign in with your account or sign up to access this lesson.

Sign In Sign Up

We show how to connect to the Azure Speech endpoint via REST using JSON, send Base64-encoded audio or upload large files to Azure storage for faster access, authenticate with API keys or Entra identities, and use the SpeechConfig and SpeechRecognizer classes with recognize_once_async to get transcriptions with per-word time offsets.

Previous Next
Previous Module The Azure Language Foundry Tools
This Module The Azure Speech Foundry Tools
Speech-Capable Applications
Speech-Capable Applications
Building Voice-Enabled AI Applications
Building Voice-Enabled AI Applications
GPT-4o Speech Models
GPT-4o Speech Models
Azure Speech in Foundry Tools
Azure Speech in Foundry Tools
Using Azure Speech APIs
Using Azure Speech APIs
Speech Synthesis Markup Language (SSML)
Speech Synthesis Markup Language (SSML)
Azure Speech MCP Server
Azure Speech MCP Server
Azure Speech Voice Live Agent
Azure Speech Voice Live Agent
Translation in Microsoft Foundry
Translation in Microsoft Foundry
Next Module Vision-Capable Multimodal Models