phone-agent
// Run a real-time AI phone agent using Twilio, Deepgram, and ElevenLabs. Handles incoming calls, transcribes audio, generates responses via LLM, and speaks back via streaming TTS. Use when user wants to: (1) Test voice AI capabilities, (2) Handle phone calls programmatically, (3) Build a conversationa
$ git log --oneline --stat
stars:370
forks:70
updated:February 19, 2026
SKILL.mdreadonly
SKILL.md Frontmatter
namephone-agent
descriptionRun a real-time AI phone agent using Twilio, Deepgram, and ElevenLabs. Handles incoming calls, transcribes audio, generates responses via LLM, and speaks back via streaming TTS. Use when user wants to: (1) Test voice AI capabilities, (2) Handle phone calls programmatically, (3) Build a conversational voice bot.
Phone Agent Skill
Runs a local FastAPI server that acts as a real-time voice bridge.
Architecture
Twilio (Phone) <--> WebSocket (Audio) <--> [Local Server] <--> Deepgram (STT)
|
+--> OpenAI (LLM)
+--> ElevenLabs (TTS)
Prerequisites
- Twilio Account: Phone number + TwiML App.
- Deepgram API Key: For fast speech-to-text.
- OpenAI API Key: For the conversation logic.
- ElevenLabs API Key: For realistic text-to-speech.
- Ngrok (or similar): To expose your local port 8080 to Twilio.
Setup
-
Install Dependencies:
pip install -r scripts/requirements.txt -
Set Environment Variables (in
~/.moltbot/.env,~/.clawdbot/.env, or export):export DEEPGRAM_API_KEY="your_key" export OPENAI_API_KEY="your_key" export ELEVENLABS_API_KEY="your_key" export TWILIO_ACCOUNT_SID="your_sid" export TWILIO_AUTH_TOKEN="your_token" export PORT=8080 -
Start the Server:
python3 scripts/server.py -
Expose to Internet:
ngrok http 8080 -
Configure Twilio:
- Go to your Phone Number settings.
- Set "Voice & Fax" -> "A Call Comes In" to Webhook.
- URL:
https://<your-ngrok-url>.ngrok.io/incoming - Method:
POST
Usage
Call your Twilio number. The agent should answer, transcribe your speech, think, and reply in a natural voice.
Customization
- System Prompt: Edit
SYSTEM_PROMPTinscripts/server.pyto change the persona. - Voice: Change
ELEVENLABS_VOICE_IDto use different voices. - Model: Switch
gpt-4o-minitogpt-4for smarter (but slower) responses.