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.
The loop
On every call, audio cycles through three stages:| Stage | You configure |
|---|---|
| STT | Provider, model, language |
| LLM | Model, system prompt, tools, knowledge bases |
| TTS | Provider, voice, speed |
What OneInbox runs for you
- Real-time audio between STT, LLM, and TTS
- End-of-speech detection
- Silence timeout and end phrases
- Transcripts and call metadata
- Telephony routing for phone calls
- Web call session tokens (
server_url,participant_token)
Call types
| Type | What it is | Guide |
|---|---|---|
| Web call | API session via POST /v1/calls/web | Web calls |
| Web SDK | Browser client that joins a web call | Web SDK |
| Outbound phone | Agent dials a number | Phone calls |
| Inbound phone | Caller reaches your number | Phone calls |
One agent, many calls
Create once. Pass per-call context withvariables — no need to clone agents.