Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Connect ElevenLabs Agents to your OpenClaw via phone with Twilio. Includes caller ID auth, voice PIN security, call screening, memory injection, and cost tracking.
Connect ElevenLabs Agents to your OpenClaw via phone with Twilio. Includes caller ID auth, voice PIN security, call screening, memory injection, and cost tracking.
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Turn your OpenClaw into a phone-callable assistant with ElevenLabs Agents + Twilio. What you get: π Call your bot from any phone π Caller ID authentication + voice PIN security π‘οΈ Call screening (whitelist-based) π§ Full memory context (loads MEMORY.md, USER.md) π° Cost tracking per call π Call transcripts with summaries β±οΈ Rate limiting π Permanent tunnel (Cloudflare) or temporary (ngrok)
Phone β Twilio β ElevenLabs Agent β Your Bridge β Anthropic Claude β OpenClaw Tools β Memory Context (MEMORY.md, USER.md) Flow: Caller dials your Twilio number Twilio routes to ElevenLabs Agent Agent sends chat completions to your bridge (mimics OpenAI API) Bridge translates to Anthropic, injects context from memory files Claude response β ElevenLabs TTS β caller hears it
OpenClaw installed and running ElevenLabs account + API key Twilio account + phone number Anthropic API key Cloudflare tunnel or ngrok (for exposing localhost)
Not needed for this skill β the bridge bypasses OpenClaw and calls Claude directly. This gives you more control over memory injection and cost tracking.
The bridge is a FastAPI server that: Accepts OpenAI-compatible /v1/chat/completions requests from ElevenLabs Injects memory context (MEMORY.md, USER.md, live data) Calls Anthropic Claude API Streams responses back in OpenAI format Logs costs and transcripts Key files: server.py β FastAPI app with /v1/chat/completions endpoint fred_prompt.py β System prompt builder (loads memory files) .env β Secrets (API keys, tokens, whitelist) contacts.json β Caller whitelist for screening
Permanent, secure alternative to ngrok: # Install cloudflared brew install cloudflare/cloudflare/cloudflared # Login and configure cloudflared tunnel login cloudflared tunnel create <tunnel-name> # Run the tunnel cloudflared tunnel --url http://localhost:8013 run <tunnel-name> Add a CNAME in Cloudflare DNS: voice.yourdomain.com β <tunnel-id>.cfargotunnel.com Or use ngrok (temporary): ngrok http 8013
Option A: Manual (UI) Go to ElevenLabs dashboard β Conversational AI Create new agent Under LLM settings β Custom LLM Set URL: https://voice.yourdomain.com/v1/chat/completions Add header: Authorization: Bearer <YOUR_BRIDGE_TOKEN> Option B: Programmatic (API) # Step 1: Store your bridge auth token as a secret curl -X POST https://api.elevenlabs.io/v1/convai/secrets \ -H "xi-api-key: YOUR_ELEVENLABS_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "type": "new", "name": "bridge_auth_token", "value": "YOUR_BRIDGE_AUTH_TOKEN" }' # Response: {"secret_id": "abc123..."} # Step 2: Create the agent curl -X POST https://api.elevenlabs.io/v1/convai/agents/create \ -H "xi-api-key: YOUR_ELEVENLABS_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "conversation_config": { "agent": { "language": "en", "prompt": { "llm": "custom-llm", "prompt": "You are a helpful voice assistant.", "custom_llm": { "url": "https://voice.yourdomain.com/v1/chat/completions", "api_key": {"secret_id": "abc123..."} } } } } }'
In ElevenLabs agent settings: Go to Phone section Enter Twilio Account SID and Auth Token Select your Twilio phone number Save Done! Your bot now answers that phone number.
Recognizes whitelisted numbers automatically: // contacts.json { "+12505551234": { "name": "Alice", "role": "family" } }
For unknown callers or high-security actions: VOICE_PIN = "banana" # Set in .env Caller must say the PIN to proceed.
Unknown numbers get a receptionist prompt: "This is Fred's assistant. I can take a message or help with general questions."
Configurable per-hour limits: RATE_LIMIT_PER_HOUR = 10 Prevents abuse and runaway costs.
The bridge auto-loads context before each call: Files read: MEMORY.md β Long-term facts about user, projects, preferences USER.md β User profile (name, location, timezone) Recent call transcripts (cross-call memory) Live data injection: Current time/date Weather (optional, via API) Calendar events (optional, via gog CLI) All injected into the system prompt before Claude sees the conversation.
Every call logs to memory/voice-calls/costs.jsonl: { "call_sid": "CA123...", "timestamp": "2026-02-03T10:30:00", "caller": "+12505551234", "duration_sec": 45, "total_cost_usd": 0.12, "breakdown": { "twilio": 0.02, "elevenlabs": 0.08, "anthropic": 0.02 } } Run analytics on the JSONL to track monthly spend.
Call your bot: Dial your Twilio number If you're whitelisted β casual conversation starts If you're unknown β receptionist mode Ask it to check your calendar, send a message, set a reminder, etc. Outbound calling (optional): curl -X POST https://voice.yourdomain.com/call/outbound \ -H "Authorization: Bearer <BRIDGE_TOKEN>" \ -d '{"to": "+12505551234", "message": "Reminder: dentist at 3pm"}'
Environment variables (.env): ANTHROPIC_API_KEY=sk-ant-... ELEVENLABS_API_KEY=sk_... ELEVENLABS_AGENT_ID=agent_... TWILIO_ACCOUNT_SID=AC... TWILIO_AUTH_TOKEN=... TWILIO_NUMBER=+1... LLM_BRIDGE_TOKEN=<random-secure-token> VOICE_PIN=<your-secret-word> CLAWD_DIR=/path/to/clawd Whitelist (contacts.json): { "+12505551234": {"name": "Alice", "role": "family"}, "+12505555678": {"name": "Bob", "role": "friend"} }
Restrict calls to business hours: # In server.py OFFICE_HOURS = { "enabled": True, "timezone": "America/Vancouver", "weekdays": {"start": "09:00", "end": "17:00"}, "weekends": False } Outside hours β voicemail prompt.
Test the bridge directly: curl -X POST https://voice.yourdomain.com/v1/chat/completions \ -H "Authorization: Bearer <BRIDGE_TOKEN>" \ -H "Content-Type: application/json" \ -d '{ "model": "claude-sonnet-4", "messages": [{"role": "user", "content": "Hello!"}], "stream": false }' Check logs: tail -f ~/clawd/memory/voice-calls/bridge.log Verify Twilio webhook: Call your number Check Twilio console β Call logs β Webhook status Should see 200 responses from ElevenLabs
Per-minute breakdown: Twilio: ~$0.01/min (inbound) + carrier fees ElevenLabs TTS: ~$0.05/min (varies by voice quality) Anthropic Claude: ~$0.01/min (depends on token usage) Total: ~$0.07-0.10/min (~$4-6/hour of talk time) Use rate limiting and call screening to control costs.
ElevenLabs official tutorial: β Basic integration β No security β No memory persistence β No cost tracking β Temporary ngrok URL This skill (Phone Voice v2.0): β All of the above β Caller ID + PIN security β Cross-call memory β Cost tracking & analytics β Permanent tunnel (Cloudflare) β Rate limiting β Call screening β Transcript logging
ElevenLabs Agents: https://elevenlabs.io/conversational-ai Twilio: https://www.twilio.com/ Cloudflare Tunnels: https://developers.cloudflare.com/cloudflare-one/connections/connect-apps/ Reference implementation: (Available on request β DM @FredMolty)
MIT β use freely, credit appreciated. Built by Fred (@FredMolty) β running on OpenClaw since 2026.
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Largest current source with strong distribution and engagement signals.