gpt-live-1

Direct from Azure models are a select portfolio curated for their market-differentiated capabilities:

• Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no third-party dependencies, backed by Azure's enterprise-grade infrastructure.
• Streamlined operations: Benefit from unified billing, governance, and seamless PTU portability across models hosted on Azure - all part of Microsoft Foundry.
• Future-ready flexibility: Access the latest models as they become available, and easily test, deploy, or switch between them within Microsoft Foundry; reducing integration effort.
• Cost control and optimization: Scale on demand with pay-as-you-go flexibility or reserve PTUs for predictable performance and savings.

Learn more about Direct from Azure models .

A bidirectional voice API that lets applications listen and speak simultaneously instead of forcing rigid turn boundaries. It is being developed as a new specialized API surface rather than a small extension of the current Realtime S2S deployment. Includes:

• Multilingual + accents across 10 languages
• Instruction following with FEM/BEM architecture
• Tool calling with FEM/BEM architecture

Supported region: Sweden Central, East US 2, Central US, France Central, South India, Canada Central

Key Features:

• Multilingual + accents across 10 languages
• Instruction following with FEM/BEM architecture
• Tool calling with FEM/BEM architecture which can be used with other gpt models for complex requests
• Human-like naturalness
• Simultaneous listen-and-speak interaction
• Configurable frontend and backend prompts
• Delegative patterns without rigid turn-taking