# Voice Call Plugin Documentation

## Overview

The Voice Call plugin enables OpenClaw to make outbound notifications and support multi-turn conversations with inbound call policies. It currently supports four providers: Twilio, Telnyx, Plivo, and a mock provider for development.

## Installation

Users can install via npm with `openclaw plugins install @openclaw/voice-call` or from a local folder for development purposes. The Gateway must be restarted after installation to load the plugin.

## Key Configuration Areas

**Provider Setup**: The plugin requires selecting a provider and configuring provider-specific credentials (account SID for Twilio, auth ID for Plivo, etc.).

**Webhook Configuration**: Twilio/Telnyx require a publicly reachable webhook URL. The plugin serves webhooks on a configurable port and path, with security options for handling proxies and tunnels.

**TTS Integration**: The plugin uses the core `messages.tts` configuration, with the ability to override it specifically for voice calls. Edge TTS is excluded from telephony due to audio format requirements.

## Inbound Calls

Inbound functionality is disabled by default but can be enabled through an allowlist policy with optional greeting and response tuning parameters.

## Access Methods

The plugin is accessible via:
- CLI commands (`openclaw voicecall call`, `continue`, `speak`, etc.)
- Agent tool named `voice_call`
- Gateway RPC endpoints