Voice Call
Start and manage outbound voice calls from an OpenClaw agent via Twilio, Telnyx, Plivo, or a mock provider.
Overview
Voice Call is an agent skill for the Build phase that starts and inspects voice calls through the OpenClaw voice-call plugin (Twilio, Telnyx, Plivo, or mock).
Install
npx skills add https://github.com/steipete/clawdis --skill voice-callWhat is this skill?
- CLI: openclaw voicecall call and status with E.164 numbers and spoken message payload
- Agent tool voice_call with initiate_call, continue_call, speak_to_user, end_call, get_status
- Providers: Twilio, Telnyx, Plivo, plus mock provider for local dev without network
- Gated on plugins.entries.voice-call.enabled and per-provider config (accountSid, apiKey, fromNumber, etc.)
- 5 voice_call tool actions: initiate_call, continue_call, speak_to_user, end_call, get_status
- 4 provider modes documented: Twilio, Telnyx, Plivo, mock
Adoption & trust: 1.9k installs on skills.sh; 378k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your OpenClaw agent needs to place real phone calls but telephony provider setup and tool actions are scattered across plugin config and CLI.
Who is it for?
Builders already on OpenClaw who want Twilio/Telnyx/Plivo wired into agent workflows with a mock fallback for development.
Skip if: Teams without OpenClaw, pure in-app WebRTC with no PSTN, or users who cannot store telephony API secrets safely.
When should I use this skill?
Start voice calls via the OpenClaw voice-call plugin or inspect call status from CLI/agent tools.
What do I get? / Deliverables
You can initiate, continue, and end agent-driven calls with documented CLI and voice_call tool actions once the plugin is enabled.
- Initiated call with retrievable call-id
- Call status and in-session message delivery via agent tool or CLI
Recommended Skills
Journey fit
Voice telephony is an integration surface wired into the agent runtime—not a launch or growth tactic by itself. Requires enabling the voice-call plugin and provider credentials under plugins.entries.voice-call—classic third-party integration work during product build.
How it compares
OpenClaw plugin integration skill—not a standalone MCP server or generic IVR designer.
Common Questions / FAQ
Who is voice-call for?
Developers shipping OpenClaw-based agents who need PSTN outbound/in-session speech via supported telephony providers.
When should I use voice-call?
During Build integrations when enabling plugins.entries.voice-call, testing mock calls locally, or wiring agent-initiated call flows before ship.
Is voice-call safe to install?
The skill uses network telephony credentials and real phone numbers; review the Security Audits panel on this Prism page and lock down secrets in plugin config.
SKILL.md
READMESKILL.md - Voice Call
# Voice Call Use the voice-call plugin to start or inspect calls (Twilio, Telnyx, Plivo, or mock). ## CLI ```bash openclaw voicecall call --to "+15555550123" --message "Hello from OpenClaw" openclaw voicecall status --call-id <id> ``` ## Tool Use `voice_call` for agent-initiated calls. Actions: - `initiate_call` (message, to?, mode?) - `continue_call` (callId, message) - `speak_to_user` (callId, message) - `end_call` (callId) - `get_status` (callId) Notes: - Requires the voice-call plugin to be enabled. - Plugin config lives under `plugins.entries.voice-call.config`. - Twilio config: `provider: "twilio"` + `twilio.accountSid/authToken` + `fromNumber`. - Telnyx config: `provider: "telnyx"` + `telnyx.apiKey/connectionId` + `fromNumber`. - Plivo config: `provider: "plivo"` + `plivo.authId/authToken` + `fromNumber`. - Dev fallback: `provider: "mock"` (no network).