让OpenClaw智能体拨打电话

Give your AI assistant a phone — OpenClaw plugin for real phone calls via Twilio + OpenAI Realtime, with in-call tools, transcripts, and …

OpenClaw Voice Call — Realtime Edition Give your AI assistant a phone. This OpenClaw plugin lets your assistant place and receive real phone calls and hold natural, full-duplex voice conversations — powered by Twilio Programmable Voice and the OpenAI Realtime API. It books your table, checks the store's hours, navigates the phone menu, gets a human on the line, wraps up politely, hangs up on its own, and reports back with a structured outcome, an AI-written summary, and the full transcript. You: "Call Luigi's and book a table for two on Friday at 7." Assistant: *dials, talks past the IVR, negotiates with the host, confirms details* Assistant: "Booked — table for 2, Friday 7pm, under your name. They said parties over 15 minutes late lose the table." Why this exists Every "AI agent" can send an email. Almost none of them can call the dry cleaner. The real world still runs on phone calls — restaurants, doctors' offices, contractors, that one store whose website hasn't been updated since 2019. This plugin closes that gap: your assistant gets a phone number, a voice, ears, a keypad, and the judgment to end the call when the job is done. Features Full conversation mode — Twilio Media Streams bridged to the OpenAI Realtime API (speech-to-speech, GA protocol). Sub-second turnaround, natural barge-in when the other party interrupts. GPT-Live runtime (opt-in, streaming.runtime: "live") — OpenAI's GPT-Live voice talks while a delegated backend model runs the call tools. Phone audio is converted between 8 kHz μ-law and 24 kHz PCM, output is paced for Twilio, and a call falls back to Realtime automatically if Live can't connect. Natural pickup and voicemail — on outbound calls the assistant waits for the other side's first words; a long greeting waits for the answering-machine verdict; voicemail is left after the beep and the call ends when it's done; phone menus are navigated without talking over them. No dead air — a lost voice session apologises and hangs up; a silent line gets one "are you still there?" and then a polite goodbye; the call wraps up a minute before its time limit; slow lookups continue in the background while the conversation goes on. In-call tools the voice AI uses autonomously: press_phone_keys — synthesized DTMF touch-tones for navigating IVR menus ("press 2 for reservations") report_call_outcome — structured result capture (status + every fact gathered: times, prices, confirmation numbers) end_call — graceful hangup: speaks a closing line, waits for it to actually play out on the line (Twilio mark echo), then disconnects. No clipped goodbyes, no lingering dead air. ask_assistant (optional) — the killer feature for scheduling: mid-call, the voice AI relays a question to your OpenClaw agent ("is Wednesday 2pm free?") and speaks the answer. Your agent answers with its full toolset — calendar, search, smart home, anything — so the phone persona stays thin and your agent stays the brain. check_calendar (optional) — zero-dependency alternative: free/busy straight from a secret iCal feed URL (Google Calendar, iCloud, Outlook, Fastmail). Only busy windows are exposed — never event titles or details. check_home / control_home (optional) — direct Home Assistant backend: read device status ("are the doors locked?") and, when enabled, control devices ("turn off the porch light") in ~1 second, bypassing the agent. Offered only on verified owner/trusted calls. ask_owner (optional) — mid-call text escalation: the AI messages you ("7pm is taken — is 8pm OK?"), you reply by text, and your answer flows back into the live call while the other party holds. Far lighter than a transfer. transfer_to_owner (optional) — when the other party genuinely needs a human (payment details, authorization), the AI announces the handoff and transfers the call to your real phone. Transcripts & summaries — every call is finalized into a Markdown transcript with an AI-generated summary and the reported outcome, including calls interrupted by a restart. Retrievable after the call via the get_transcript tool action. Call recording (optional, off by default) — a stereo WAV per call (the other party / the assistant as heard), transcribed into the call's transcript. See the consent note below. Owner tools from the Voice Bridge (optional) — on calls with the verified owner: research into the owner's own projects ("explain"), project discussions, and answers delivered by text. Post-call reports (optional) — when a call ends, your OpenClaw agent is briefed automatically: it messages you the result and performs obvious follow-ups (adds the confirmed booking to your calendar, notes a needed retry). Calls stop being fire-and-forget. Answering-machine detection (optional) — Twilio async AMD tells the plugin definitively when voicemail picked up; policy decides: leave a concise message after the beep (default), hang up, or continue as normal. Semantic turn detection (optional) — semantic_vad understands when a speaker has finished a thought rather than just paused, for fewer interruptions and more natural conversations. Call screening awareness — handles Google Call Screen and voicemail gatekeepers by identifying itself with a configurable identity phrase. Goal-directed calls — pass talking_points and call_party (first-party vs third-party) and the AI stays on task: cover the points, collect the answers, confirm out loud, wrap up. Inbound calls (optional) — allowlist-gated with layered identity verification: SHAKEN/STIR attestation (the carrier cryptographically vouches for the caller ID, defeating spoofing) and an optional spoken access phrase checked by a tool — the phrase never enters the model prompt. Device profiles — per-caller policies: response length, forbidden actions, extra instructions. Hardened by default — Twilio webhook signature verification, per-call stream auth tokens, pre-auth connection throttling, SSRF-guarded provider API calls, call-duration safety caps, stale-call reaping. Providers — Twilio (recommended,