Orbitali Docs

Welcome to Orbitali

The platform to build and run production-ready AI voice agents.

Orbitali is the platform to build, deploy, and operate production-ready AI voice agents. It provides a managed real-time voice stack, carrier integrations, tools, knowledge, transcripts, and observability while leaving your business logic in your own backend.


Why Orbitali?

Orbitali manages the real-time voice stack end to end. Speech-to-text (STT), language model (LLM), and text-to-speech (TTS) components run under the hood and are optimized as one service. Orbitali also handles bidirectional audio streaming, turn-taking, interruptions, model orchestration, and tool execution.

You configure the agent's identity, instructions, language, voice, tools, knowledge, and channels instead of selecting and maintaining individual model providers. The underlying providers are implementation details that Orbitali manages and may evolve over time.


Core Capabilities

1. Voice Telephony

Orbitali uses a Bring Your Own Carrier (BYOC) model. You lease and maintain phone numbers directly in your Twilio or Telnyx accounts, then configure them to route calls to Orbitali. You pay the carriers directly for connection minutes without any Orbitali markup. Your Orbitali plan includes a monthly voice-minute allowance; extra usage is billed at €0.10 per minute in 10-second increments, rounded up.

[!NOTE] Orbitali supports inbound calls, browser voice sessions, and individual outbound Telnyx or Twilio calls through the dashboard, API, or MCP. Cold-call campaign management is not supported.

2. Built-in Knowledge Base (RAG)

You can upload company policies, product sheets, or FAQ documents in text, Markdown, or PDF format. Orbitali indexes the content for semantic retrieval, and your agent uses the built-in search_knowledge tool to answer questions without requiring you to build a separate search API.

3. Custom Tools & Webhooks

For database lookups or transactional flows (e.g., checking appointment availability, booking a table, or looking up an invoice), your agent can trigger custom tools. Webhook tools are delivered as agent:tool-call events to your configured Server URL; direct HTTP tools call the endpoint configured on the tool. This lets you connect a backend, CRM, or database while keeping business logic outside Orbitali.

For call start, end, and summary notifications across all agent types, configure organization call lifecycle webhooks in Settings → Webhooks. These are separate from agent tool webhooks.

4. Ephemeral Browser Calling

If you need voice experiences directly in your mobile app or website, Orbitali supports direct browser calling. Your backend generates an ephemeral session token, and your frontend connects directly to the voice runtime via WebSockets to stream microphone audio.

5. Embeddable Web Chat

Studio and Agency plans can expose an agent through an embeddable web-chat widget. The chat uses the agent's configured instructions and knowledge, and the dashboard provides the script snippet and conversation history. See the current pricing page for plan allowances and branding options.


Platform Responsibilities

What Orbitali HandlesWhat Your Backend Handles
Bidirectional telephony media streamingBusiness logic and private data
Real-time ASR, LLM reasoning, and TTS synthesisAPI endpoints or webhook handlers for custom actions (optional)
Active listening, barge-in, and interruption cut-offsEphemeral session token generation
Local document chunking, indexing, and vector searchDynamic prompt construction (optional)
Call history records, tool execution logs, and usage trackingPost-call automation (CRMs, scheduling systems)

Next Steps

  • Quickstart: Deploy your first voice agent using the dashboard or API.
  • Concepts: Understand the architecture of agents, prompts, tools, and sessions.
  • Guides: Choose between static, HTTP, and webhook agents, then follow the matching setup guide.
  • API Reference: Create, activate, and test an agent with complete API examples.

On this page