Documentation Index
Fetch the complete documentation index at: https://docs.oneinbox.ai/llms.txt
Use this file to discover all available pages before exploring further.
What is OneInbox?
OneInbox is a voice orchestration platform for building AI agents that handle live voice conversations over the phone and the web. This documentation covers the REST API and how to integrate OneInbox into your product. You configure agents, models, and calls with API requests — OneInbox handles real-time audio, telephony, and scaling. Base URL:https://api.oneinbox.ai
How voice agents work
Every call runs a loop until the conversation ends:| Layer | You configure |
|---|---|
| STT | Provider, model, language |
| LLM | Model, system prompt, tools, knowledge bases |
| TTS | Provider, voice, speed |
| Term | Meaning |
|---|---|
| STT (speech-to-text) | Converts what the caller says into text |
| LLM (language model) | Decides what the agent should reply |
| TTS (text-to-speech) | Converts the agent’s text reply into spoken audio |
What you can build
- Outbound callers — your agent dials leads, qualifies them, or sends reminders
- Inbound support — assign a phone number; callers reach your agent 24/7
- Web voice — embed a voice widget on your site with the OneInbox Web SDK
Get started
Quickstart
Build your first voice agent in 3 steps (~15 min)
API reference
Every endpoint with interactive Try It examples
Next steps
- Quickstart — prerequisites, 3-step path, and curl walkthrough
- How it works — the voice pipeline explained
- Agents — STT, LLM, TTS, and call behavior