Skip to main content
Pipecat is an open-source voice pipeline you host yourself. There are two ways to use it with Unpod:
  • Your Pipecat bot on an Unpod call. Unpod carries the phone call and streams its audio to your bot; your pipeline does STT, the LLM and TTS. Jump to the walkthrough.
  • The Unpod brain inside your Pipecat pipeline, below.
Unlike the SIP-trunk providers, you don’t configure Pipecat as a carrier - instead you drop the Unpod brain into a Pipecat pipeline as a FrameProcessor. Audio that Pipecat captures flows through your DialogMachine, and the reply streams back out the same pipeline.
Pipecat is a runtime, not a SIP provider. There’s no Dashboard/API provider config - you wire it in code. The full, working integration lives in the embedding guide.

Pipecat embedding guide

The drop-in FrameProcessor, install steps, and a complete pipeline example.

How it fits

🎙️Mic / SIP audioAny Pipecat transport
① frames
⚙️Pipecat pipelineSTT · VAD · TTS stages
② user turn③ reply tokens
🧠Unpod FrameProcessorDialogMachine
④ TTS stream
🔊Audio outLow-latency reply
  • Bring audio in - any Pipecat transport (WebRTC, Daily, telephony) feeds frames.
  • Insert the brain - add the Unpod FrameProcessor so each user turn drives your DialogMachine.
  • Stream the reply - tokens stream back through Pipecat’s TTS stage for low latency.

Your Pipecat bot on an Unpod call

Unpod answers the call and asks your answer URL what to do. You reply with <Stream>, Unpod opens a WebSocket to your bot, and UnpodFrameSerializer turns its messages into Pipecat frames and back. The rest of your bot is plain Pipecat. The protocol underneath is on Audio Streaming.
Preview. Your org needs the Call API and audio streaming switched on. Ask the Unpod team.
1

Credentials and install

Export UNPOD_BASE_URL, UNPOD_PLATFORM_TOKEN and UNPOD_ORG_HANDLE as shown in Credentials. Python 3.12+.
The bot below uses Deepgram, Anthropic and Cartesia; export DEEPGRAM_API_KEY, ANTHROPIC_API_KEY and CARTESIA_API_KEY, or swap in any Pipecat services.
2

Get a number and your webhook secret

Attach a number with attach_type="human_call" so your app answers it. Then get your org’s webhook secret: create it once with webhook_secret.rotate(), or read the current one with webhook_secret.reveal() (org admin). Store it as UNPOD_WEBHOOK_SECRET. Unpod signs the stream’s WebSocket upgrade with it, so your bot only accepts streams from Unpod.
Rotating invalidates the previous secret. If your org already has one, use reveal().
3

Run the bot

One app, two routes: /answer replies with <Stream>, and /ws is the stream. Save as app.py:
app.py
Run it with python app.py.
4

Expose it

Unpod only calls public https URLs, and streams to a public ws:// or wss:// host (use wss:// in production). In a second terminal:
Set PUBLIC_HOST to the ngrok host (e.g. abc123.ngrok.app) and restart app.py.
5

Point your number at it, or call out

Inbound, once per number:
Outbound, per call:
6

Talk to it

Call your number, or pick up the outbound call. The bot greets you; talk and it answers. When the caller hangs up, Unpod closes the socket and the pipeline stops. When the bot ends (an EndFrame), the serializer hangs up the call.
A fuller example, with outbound calls started from a POST /start route protected by an X-Api-Key header, is in the SDK repo: examples/pipecat_streaming.

What UnpodFrameSerializer does

  • It reads the format from start: μ-law or A-law at 8000 Hz, or L16 at 8000, 16000 or 24000 Hz. Run the pipeline at 8000 Hz for μ-law and A-law calls to skip resampling.
  • It feeds only the caller’s (inbound) audio to the pipeline, so the bot never hears itself even with audioTrack="both".
  • Hanging up needs client= (an AsyncClient) or your own hangup= coroutine. A call that already ended (404, 409, 410) is ignored. Turn it off with params=UnpodFrameSerializer.InputParams(auto_hang_up=False).

When to pick Pipecat

Bring your agent

The adapter pattern any runtime uses.

All platforms

Back to the integrations overview.