SIPHON
Build calling agents in minutes, not months
Voice AI demos are everywhere.
You call a number, an enthusiastic robot voice greets you, and you have a pleasant five-minute chat about the weather or the meaning of life. But the moment you ask:
“Can you squeeze me in for a cleaning next Tuesday at 2 PM?”
…the magic usually breaks.
Why?
Because talking is easy. Context is hard.
Most voice agents are great conversationalists, but they operate in a vacuum. They have no real understanding of time, availability, or the systems businesses actually run on.
To build a truly useful AI receptionist, you don’t just need a good LLM—you need real integrations.
That’s why we’re introducing Native Google Calendar Integration in SIPHON.
The Context Gap in Voice Agents
Traditionally, building a scheduling voice agent looks something like this:
Transcription – Convert speech to text
Extraction – Parse phrases like “next Tuesday at 2 PM”
API Glue – Authenticate with Google, fetch events, check conflicts
Response Logic – Manually construct confirmations and retries
This approach is fragile, slow to build, and painful to maintain.
SIPHON solves this by treating integrations as first-class citizens—just like your LLM, STT, or TTS provider.
Native Google Calendar Integration
With SIPHON, enabling Google Calendar support is a single line of configuration:
agent = Agent(google_calendar=True )
That’s it.
No OAuth boilerplate.
No custom API clients.
No fragile glue code.
What This Enables
Once enabled, your SIPHON agent can:
Check real-time availability before offering time slots
Create, update, and cancel events directly on Google Calendar
Avoid double-booking and intelligently handle conflicts
Reschedule appointments in a natural conversation
All through voice.
A Real Example: 24/7 Dental Clinic Receptionist
To showcase this integration, we built a production-ready Dental Clinic Receptionist.
This is not a toy demo—it behaves like a real front-desk employee:
Inbound Call – A patient calls to book an appointment
Verification – The agent verifies whether the caller is a new or existing patient
Smart Scheduling – It checks the dentist’s actual Google Calendar
Booking – The agent books the slot and confirms it verbally
Follow-ups – Patients can call back to modify or cancel appointments
Explore the full example on GitHub
Why This Matters
For Voice AI to move from novelty to utility, it must do real work.
Scheduling is one of the highest-value automation targets for:
Clinics and hospitals
Salons and service businesses
Consultants and small teams
By abstracting away OAuth flows, API management, and tool orchestration, SIPHON lets developers build powerful scheduling agents in minutes instead of weeks.
Get Started
Ready to give your voice agent a calendar?
SIPHON is an open-source framework for building production-grade calling AI.
⭐ Star us on GitHub
Three months.
That’s how long many teams spend building telephony infrastructure before writing a single line of actual conversation logic for an AI voice agent.
Not because the AI was hard.
Because telephony is brutal.
Today, we’re open-sourcing the solution so you don’t have to go through the same pain.
The Hidden Problem with AI Calling Agents
Building an AI calling agent sounds straightforward:
Use an LLM
Add speech-to-text
Add text-to-speech
Connect it to a phone number
In reality, that’s where most teams hit a wall.
To make real phone calls, you end up dealing with:
SIP trunks & PSTN providers
Low-latency, bidirectional audio
Real-time orchestration of STT, LLM, and TTS
Call state, interruptions, transfers
Scaling, monitoring, recordings, persistence
The result?
Most teams spend weeks or months on infrastructure before they ever touch the conversation itself.
We did too. And eventually asked:
“Why is building voice AI still this hard?”
Introducing Siphon
Siphon is an open-source Python framework that handles the telephony complexity for you, so you can focus on building great conversations.
Here’s what a complete AI receptionist looks like with Siphon:
from siphon.agent import Agent
from siphon.plugins import openai, cartesia, deepgram
agent = Agent(
agent_name="receptionist",
llm=openai.LLM(model="gpt-4"),
tts=cartesia.TTS(voice="helpful-assistant"),
stt=deepgram.STT(model="nova-2"),
system_instructions="""
You are a friendly receptionist for Acme Corp.
Help callers schedule appointments or route them correctly.
"""
)
if name == "__main__":
agent.start()
Run this, and your agent can answer real phone calls via any SIP provider (Twilio, Telnyx, etc.).
What Siphon Handles for You
🔌 SIP & PSTN connectivity
Works with any SIP provider, no FreeSWITCH pain.⚡ Real-time audio pipeline
Built on LiveKit with streaming audio and sub-500ms voice-to-voice latency.🤖 AI orchestration
Plug-and-play support for LLMs, STT, and TTS.
Swap providers with a single line:
llm=anthropic.LLM(model="claude-3-5-sonnet")
📈 Production-ready by default Auto-scaling, call recordings, transcripts, state handling, and observability.
Quick Start
Install:
pip install siphon-ai
Create an agent:
from siphon.agent import Agent
from siphon.plugins import openai, cartesia, deepgram
agent = Agent(
agent_name="my_first_agent",
llm=openai.LLM(),
tts=cartesia.TTS(),
stt=deepgram.STT(),
system_instructions="You are a helpful assistant.",
)
agent.start()
That’s it.
Your agent is live and answering phone calls.
(Full setup, outbound calling, and advanced examples are in the docs.)
Why We Open-Sourced It
We could’ve kept Siphon proprietary or turned it into a closed SaaS.
But we believe voice AI shouldn’t be locked behind massive infrastructure effort.
Siphon is:
Apache 2.0 licensed
Provider-agnostic
Fully self-hostable
No vendor lock-in
Use it commercially, modify it, or build on top of it.
What You Can Build
📞 Customer support agents
📅 Appointment scheduling
💼 Sales qualification
📊 Surveys & feedback collection
🏥 Healthcare intake systems
If it involves phone calls and conversations, Siphon handles the hard parts.
Get Involved
⭐ GitHub: https://github.com/blackdwarftech/siphon
📖 Docs: https://siphon.blackdwarf.in/docs
🐛 Issues & feature requests welcome
🤝 PRs encouraged
We’re building Siphon in public and would love community feedback.
If you’ve ever thought
“I wish building AI calling agents was simpler”
— give Siphon a try.
Built by BLACKDWARF
Mission: Democratize complex technologies for developers.
Comment