6 custom skills (assign-task, dispatch-webhook, daily-briefing, task-capture, qmd-brain, tts-voice) with technical documentation. Compatible with Claude Code, OpenClaw, Codex CLI, and OpenCode.
29 lines
1.4 KiB
Markdown
29 lines
1.4 KiB
Markdown
# 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
|