Welcome to LuMay Docs

Everything you need to build, deploy, and scale AI-powered voice agents. Explore our APIs, SDK guides, and reference documents.

Build with LuMay

Core speech components to configure, record, and synthesize dialogue.

Voice Agents

Create AI agents that handle inbound and outbound voice calls with natural conversation.

Speech to Text

Real-time and pre-recorded speech recognition with multi-provider support.

Text to Speech

100+ neural voices across ElevenLabs, Deepgram, Azure, Google, and OpenAI.

Platform & Capabilities

Workflow tools, connector endpoints, and analytics logging.

Tools & Integrations

MCP, API, and Connector tools that give your agents real-time capabilities.

Pipeline & Workflows

Dynamic STT → LLM → TTS pipeline builder with drag-and-drop flow design.

Call Management & Analytics

Track and direct every live call with granular API session control, transcripts, and logs.

Deployment Guides

Production configurations for inbound trunks, outbound outreach, and compliance.

Integration Guides

Step-by-step production setups for setting up inbound trunks and outbound campaigns.

Direct API Reference

Direct HTTP access to every LuMay capability. JSON in, JSON out.

REST API Reference

Direct HTTP access to every LuMay capability. JSON in, JSON out.

Utilities & WebSockets

Bidirectional channels, hooks, and operational notes.

Security & Control

OIDC auth, RBAC, audit logs, encrypted credentials, multi-tenant isolation.

Webhooks

Subscribe to real-time events: call lifecycle, agent updates, transcripts.

WebSockets

Low-latency bidirectional streaming for real-time voice and event data.

Developer Support

Review support targets, developer SLAs, and SLAs.