Meet the Omniagent API
The foundational layer powering multimodal coworkers across every surface your customer touches. Create an Omniagent — an AI agent with a persistent identity, voice, and visual appearance that carries its knowledge, memory, and actions across website, apps, phone, and beyond. One API, one agent, every channel.
From API key to first Omniagent in minutes
Follow the path. Each step links to the in-depth resource you need.
Get an API key
Create a resource in the Azure Portal to set up your subscription, then generate an API key from the dashboard. Once you have a key, see Authentication for details on how to authenticate API calls.
Build
Pick a companion, add knowledge and tools, configure voice and settings — then create your Omniagent.
Deploy
Choose a channel — WebRTC, WebSocket, or SIP — and go live. Same agent, every surface.
Monitor
Track sessions, review transcripts, and refine your agent over time.
Explore by topic
Identity
Define your agent's role, persona, voice, and visual appearance. Consistent across every session and channel.
Knowledge
Give your agent domain expertise with files, FAQs, and structured data.
Memory
Your agent remembers who it's talking to — across sessions and channels.
Actions
Connect your agent to real systems through tools and functions.
WebRTC
Browser-based voice and video via the Web SDK.
WebSockets
Audio-only streaming for apps and custom integrations.
SIP
Answer incoming phone calls over SIP.
Capabilities
| Capability | Details |
|---|---|
| Real-time video avatars | 2D avatars with lip sync and natural expressions |
| Persistent identity and memory | Agents maintain a consistent persona and remember users across sessions and channels |
| Tool integration | Connect agents to real systems through custom functions to trigger workflows, generate content, and more |
| Model-agnostic | Bring your own Azure OpenAI Real-Time deployment, or use a Napster-managed one |
| Web SDK | Works with React, Vue, Angular, or vanilla JS; mount a companion in any DOM container |
| Low latency | ~300ms response times |
| Multilingual | ~30 languages supported |
| 2,000+ companions | Pre-built expert agents, or wire your own knowledge base and tools |
| Built-in safety | Content moderation, crisis detection, topic restrictions, and auditability are always active |
Compliance and security
- SOC 2 Type II — report available under NDA
- GDPR & CCPA — US and EU data protection
- Encryption — AES + TLS 1.2+ at rest and in transit
- Pen testing — annual third-party security audits
- Data residency — regional options for enterprise
- Tenant isolation — your data stays in your environment; no cross-customer data mixing, no training on your data