Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Explore the next generation of Azure Speech capabilities in this 45-minute conference talk from Microsoft Ignite 2025. Discover how to build voice-enabled applications, intelligent customer-service AI agents, and multimodal translation tools using cutting-edge speech technologies. Learn about the generally available Voice Live API for creating real-time voice agents and explore new APIs that leverage large language models to unlock advanced capabilities. Examine partnerships utilizing Azure Speech for enhanced voice experiences and understand the launch of the LLM Speech API with improved transcription and context understanding. Master the selection of generative AI models and prompt setup for voice agents while witnessing demonstrations of custom speech models, audio enhancements, and voice options. Investigate AI assistant improvements featuring natural conversation and adaptive behavior, and discover the introduction of 41 upgraded Neural HD voices supporting 100 locales. Learn techniques for creating branded voices and custom avatars using new HD voice models, addressing audio interruptions, and ensuring clear voice recognition in various scenarios including healthcare applications. Gain insights into future expansion and innovation plans, including real-time translation capabilities that will shape the next wave of voice-enabled applications.
