Add standalone Daily + Twilio SIP example

This commit is contained in:
Mark Backman
2025-04-26 09:42:20 -04:00
parent 4513e81e13
commit 97c28989c1
6 changed files with 434 additions and 0 deletions

View File

@@ -0,0 +1,88 @@
# Daily + Twilio SIP Voice Bot
This project demonstrates how to create a voice bot that can receive phone calls via Twilio and use Daily's SIP capabilities to enable voice conversations.
## How It Works
1. Twilio receives an incoming call to your phone number
2. Twilio calls your webhook server (`/call` endpoint)
3. The server creates a Daily room with SIP capabilities
4. The server starts the bot process with the room details
5. The caller is put on hold with music
6. The bot joins the Daily room and signals readiness
7. Twilio forwards the call to Daily's SIP endpoint
8. The caller and bot are connected, and the bot handles the conversation
## Prerequisites
- A Daily account with an API key
- A Twilio account with a phone number that supports voice
- OpenAI API key for the bot's intelligence
- ElevenLabs API key for text-to-speech (optional but recommended)
## Setup
1. Create a virtual environment and install dependencies
```bash
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
pip install -r requirements.txt
```
2. Set up environment variables
Copy the example file and fill in your API keys:
```bash
cp .env.example .env
# Edit .env with your API keys
```
3. Configure your Twilio webhook
In the Twilio console:
- Go to your phone number's configuration
- Set the webhook for "A Call Comes In" to your server's URL + "/call"
- For local testing, you can use ngrok to expose your local server
```bash
ngrok http 8000
# Then use the provided URL (e.g., https://abc123.ngrok.io/call) in Twilio
```
## Running the Server
Start the webhook server:
```bash
python server.py
```
## Testing
Call your Twilio phone number. The system should answer the call, put you on hold briefly, then connect you with the bot.
## Customizing the Bot
You can customize the bot's behavior by modifying the system prompt in `bot.py`.
## Troubleshooting
### Call is not being answered
- Check that your Twilio webhook is correctly configured
- Verify your Twilio account has sufficient funds
- Check the logs of both the server and bot processes
### Call connects but no bot is heard
- Ensure your Daily API key is correct and has SIP capabilities
- Check that the SIP endpoint is being correctly passed to the bot
- Verify that the ElevenLabs API key and voice ID are correct
### Bot starts but disconnects immediately
- Check the Daily and Twilio logs for any error messages
- Ensure your server has stable internet connectivity

View File

@@ -0,0 +1,153 @@
"""Twilio + Daily voice bot implementation."""
import argparse
import asyncio
import os
import sys
from dotenv import load_dotenv
from loguru import logger
from twilio.rest import Client
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.services.daily import DailyParams, DailyTransport
# Setup logging
load_dotenv()
logger.remove(0)
logger.add(sys.stderr, level="DEBUG")
# Initialize Twilio client
twilio_client = Client(os.getenv("TWILIO_ACCOUNT_SID"), os.getenv("TWILIO_AUTH_TOKEN"))
async def run_bot(room_url: str, token: str, call_id: str, sip_uri: str) -> None:
"""Run the voice bot with the given parameters.
Args:
room_url: The Daily room URL
token: The Daily room token
call_id: The Twilio call ID
sip_uri: The Daily SIP URI for forwarding the call
"""
logger.info(f"Starting bot with room: {room_url}")
logger.info(f"SIP endpoint: {sip_uri}")
# Setup the Daily transport
transport = DailyTransport(
room_url,
token,
"Phone Bot",
DailyParams(
audio_in_enabled=True,
audio_out_enabled=True,
transcription_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
)
# Setup TTS service
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
)
# Setup LLM service
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
# Initialize LLM context with system prompt
messages = [
{
"role": "system",
"content": (
"You are a friendly phone assistant. Your responses will be read aloud, "
"so keep them concise and conversational. Avoid special characters or "
"formatting. Begin by greeting the caller and asking how you can help them today."
),
},
]
# Setup the conversational context
context = OpenAILLMContext(messages)
context_aggregator = llm.create_context_aggregator(context)
# Build the pipeline
pipeline = Pipeline(
[
transport.input(),
context_aggregator.user(),
llm,
tts,
transport.output(),
context_aggregator.assistant(),
]
)
# Create the pipeline task
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True # Enable barge-in so callers can interrupt the bot
),
)
# Handle participant joining
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
logger.info(f"First participant joined: {participant['id']}")
await transport.capture_participant_transcription(participant["id"])
await task.queue_frames([context_aggregator.user().get_context_frame()])
# Handle participant leaving
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
logger.info(f"Participant left: {participant['id']}, reason: {reason}")
await task.cancel()
# Handle call ready to forward
@transport.event_handler("on_dialin_ready")
async def on_dialin_ready(transport, cdata):
logger.info(f"Forwarding call {call_id} to {sip_uri}")
try:
# Update the Twilio call with TwiML to forward to the Daily SIP endpoint
twilio_client.calls(call_id).update(
twiml=f"<Response><Dial><Sip>{sip_uri}</Sip></Dial></Response>"
)
logger.info("Call forwarded successfully")
except Exception as e:
logger.error(f"Failed to forward call: {str(e)}")
raise
# Run the pipeline
runner = PipelineRunner()
await runner.run(task)
async def main():
"""Parse command line arguments and run the bot."""
parser = argparse.ArgumentParser(description="Daily + Twilio Voice Bot")
parser.add_argument("-u", type=str, required=True, help="Daily room URL")
parser.add_argument("-t", type=str, required=True, help="Daily room token")
parser.add_argument("-i", type=str, required=True, help="Twilio call ID")
parser.add_argument("-s", type=str, required=True, help="Daily SIP URI")
args = parser.parse_args()
# Validate required arguments
if not all([args.u, args.t, args.i, args.s]):
logger.error("All arguments (-u, -t, -i, -s) are required")
parser.print_help()
sys.exit(1)
await run_bot(args.u, args.t, args.i, args.s)
if __name__ == "__main__":
asyncio.run(main())

View File

@@ -0,0 +1,11 @@
# Daily credentials
DAILY_API_KEY=your_daily_api_key
DAILY_API_URL=https://api.daily.co/v1
# Twilio credentials
TWILIO_ACCOUNT_SID=your_twilio_account_sid
TWILIO_AUTH_TOKEN=your_twilio_auth_token
# Service keys
OPENAI_API_KEY=your_openai_api_key
CARTESIA_API_KEY=your_cartesia_api_key

View File

@@ -0,0 +1,5 @@
pipecat-ai[daily,elevenlabs,openai,silero]
fastapi==0.115.6
uvicorn
python-dotenv
twilio

View File

@@ -0,0 +1,111 @@
"""Webhook server to handle Twilio calls and start the voice bot."""
import os
import shlex
import subprocess
from contextlib import asynccontextmanager
import aiohttp
import uvicorn
from dotenv import load_dotenv
from fastapi import FastAPI, HTTPException, Request
from fastapi.responses import PlainTextResponse
from twilio.twiml.voice_response import VoiceResponse
from utils.daily_helpers import create_sip_room
# Load environment variables
load_dotenv()
# Initialize FastAPI app with aiohttp session
@asynccontextmanager
async def lifespan(app: FastAPI):
# Create aiohttp session to be used for Daily API calls
app.session = aiohttp.ClientSession()
yield
# Close session when shutting down
await app.session.close()
app = FastAPI(lifespan=lifespan)
@app.post("/call", response_class=PlainTextResponse)
async def handle_call(request: Request):
"""Handle incoming Twilio call webhook."""
print("Received call webhook from Twilio")
try:
# Get form data from Twilio webhook
form_data = await request.form()
data = dict(form_data)
# Extract call ID (required to forward the call later)
call_sid = data.get("CallSid")
if not call_sid:
raise HTTPException(status_code=400, detail="Missing CallSid in request")
print(f"Processing call with ID: {call_sid}")
# Create a Daily room with SIP capabilities
try:
room_details = await create_sip_room(request.app.session)
except Exception as e:
print(f"Error creating Daily room: {e}")
raise HTTPException(status_code=500, detail=f"Failed to create Daily room: {str(e)}")
# Extract necessary details
room_url = room_details["room_url"]
token = room_details["token"]
sip_endpoint = room_details["sip_endpoint"]
# Make sure we have a SIP endpoint
if not sip_endpoint:
raise HTTPException(status_code=500, detail="No SIP endpoint provided by Daily")
# Start the bot process
bot_cmd = f"python bot.py -u {room_url} -t {token} -i {call_sid} -s {sip_endpoint}"
try:
# Use shlex to properly split the command for subprocess
cmd_parts = shlex.split(bot_cmd)
# CHANGE: Keep stdout/stderr for debugging
# Start the bot in the background but capture output
subprocess.Popen(
cmd_parts,
# Don't redirect output so we can see logs
# stdout=subprocess.DEVNULL,
# stderr=subprocess.DEVNULL
)
print(f"Started bot process with command: {bot_cmd}")
except Exception as e:
print(f"Error starting bot: {e}")
raise HTTPException(status_code=500, detail=f"Failed to start bot: {str(e)}")
# Generate TwiML response to put the caller on hold with music
resp = VoiceResponse()
resp.play(
url="http://com.twilio.sounds.music.s3.amazonaws.com/MARKOVICHAMP-Borghestral.mp3",
loop=10,
)
return str(resp)
except HTTPException:
raise
except Exception as e:
print(f"Unexpected error: {str(e)}")
raise HTTPException(status_code=500, detail=f"Server error: {str(e)}")
@app.get("/health")
async def health_check():
"""Simple health check endpoint."""
return {"status": "healthy"}
if __name__ == "__main__":
# Run the server
port = int(os.getenv("PORT", "8000"))
print(f"Starting server on port {port}")
uvicorn.run("server:app", host="0.0.0.0", port=port, reload=True)

View File

@@ -0,0 +1,66 @@
"""Helper functions for interacting with the Daily API."""
import os
from typing import Any, Dict, Optional
import aiohttp
from dotenv import load_dotenv
from pipecat.transports.services.helpers.daily_rest import (
DailyRESTHelper,
DailyRoomParams,
DailyRoomProperties,
DailyRoomSipParams,
)
load_dotenv()
# Initialize Daily API helper
async def get_daily_helper(session: Optional[aiohttp.ClientSession] = None) -> DailyRESTHelper:
"""Get a Daily REST helper with the configured API key."""
if session is None:
session = aiohttp.ClientSession()
return DailyRESTHelper(
daily_api_key=os.getenv("DAILY_API_KEY", ""),
daily_api_url=os.getenv("DAILY_API_URL", "https://api.daily.co/v1"),
aiohttp_session=session,
)
async def create_sip_room(session: Optional[aiohttp.ClientSession] = None) -> Dict[str, str]:
"""Create a Daily room with SIP capabilities for phone calls."""
daily_helper = await get_daily_helper(session)
# Configure SIP parameters
sip_params = DailyRoomSipParams(
display_name="phone-user",
video=False,
sip_mode="dial-in",
num_endpoints=1,
)
# Create room properties with SIP enabled
properties = DailyRoomProperties(
sip=sip_params,
enable_dialout=True, # Needed for outbound calls if you expand the bot
enable_chat=False, # No need for chat in a voice bot
start_video_off=True, # Voice only
)
# Create room parameters
params = DailyRoomParams(properties=properties)
# Create the room
try:
room = await daily_helper.create_room(params=params)
print(f"Created room: {room.url} with SIP endpoint: {room.config.sip_endpoint}")
# Get token for the bot to join
token = await daily_helper.get_token(room.url, 24 * 60 * 60) # 24 hours validity
return {"room_url": room.url, "token": token, "sip_endpoint": room.config.sip_endpoint}
except Exception as e:
print(f"Error creating room: {e}")
raise