Public PyPI plugin

PyAI vs Pipecat: managed agent or custom pipeline

Yes. `pip install pipecat-pyai`. Your pipeline keeps the transport, LLM, and processors. PyAI is Hear and Speak.

Get API Key Setup guide

PyAI

Omni

PyAI runs the agent.

Pipecat

Your loop

You keep transport, LLM, and tools. PyAI is speech.

Control boundary

The decision is who operates the conversation loop.

Both paths use PyAI speech. The difference is whether your application owns each stage or asks Omni to run the agent as one managed system.

Managed path

PyAI Omni

1Connect to Omni over one WebSocket.
2Configure persona, knowledge, tools, voice, and optional continuity when the Agent profile has it enabled and a caller key is available.
3PyAI runs turn-taking, speech, reasoning, and agent audio.
4Use managed telephony or connect your own call path.

Composable path

Pipecat + PyAI

1Keep your existing Pipecat transport.
2Place PyAI Hear after transport input.
3Run context, LLM, tools, and custom processors in your pipeline.
4Place PyAI Speak before transport output.

Side by side

	PyAI	Pipecat + PyAI
Product shape	Managed speech-to-speech agent on one WebSocket.	Open-source Python pipeline with tested public PyAI STT and TTS services.
What you own	Persona, tools, knowledge, and business configuration.	Transport, processors, context, LLM, turn policy, deployment, and failure handling.
Control model	Configure the agent, then stream caller audio.	Place, branch, inspect, or replace processors frame by frame.
Speech	Speech is part of the integrated Omni path.	PyAI Hear and Speak are explicit services in the pipeline.
Deployment	PyAI operates the realtime agent service.	Self-host the bot or deploy it through Pipecat Cloud.
Runtime	Any client that can speak the Omni WebSocket protocol.	Python. The PyAI service package requires Python 3.11 or newer.

Pipecat facts are from its public framework, pipeline, transport, and Cloud documentation, checked August 17, 2026.

The working object

Keep your pipeline. Replace the STT and TTS processors.

Your framework still owns orchestration. The PyAI key stays on the server-side worker and authorizes Hear and Speak.

Install the PyAI adapter

pip install pipecat-pyai==0.1.2

Set PYAI_API_KEY on the worker. A sandbox key is enough to test Hear and Speak with bounded daily usage and no billing gate.

Open the complete guide

Python

from pipecat.pipeline.pipeline import Pipeline
from pipecat_pyai import PyAISTTService, PyAITTSService

pipeline = Pipeline([
    transport.input(),
    PyAISTTService(language="en"),
    user_aggregator,
    llm,
    PyAITTSService(voice="stock_emma_en_gb"),
    transport.output(),
    assistant_aggregator,
])

Choose based on the work you want to own.

Choose Pipecat + PyAI when

You need custom processors between any two stages.
You want explicit control over frames, branching, and transports.
You already operate a Pipecat application.
Your team accepts owning pipeline deployment and failure policy.

Choose PyAI Omni when

You are shipping a phone-first voice agent.
You want one realtime contract instead of a service pipeline.
You want built-in call controls, knowledge, tools, and caller continuity when the Agent profile has it enabled and a caller key is available.
You want PyAI to operate the full conversation loop.

Sources

Pipecat framework overview

Open-source Python framework, agent services, transports, and deployment choices.

Pipecat pipeline

Frame processor order, data flow, and component swapping.

Pipecat Cloud

Optional managed deployment and usage-based infrastructure.

TL;DR

Keep the Pipecat frame pipeline and swap only STT and TTS
Hear is $0.001/min and Speak is $0.04/min as explicit services
Use Omni at $0.05/min speech + brain when you want one managed socket
Choose Pipecat when custom processors and branching are the point

When Pipecat is the better pick

The public services support Python. Pipecat puts pipeline behavior in your application, so your team also owns more integration and operational work.

FAQ

Can I use PyAI with Pipecat?

Yes. Install pipecat-pyai in your Python worker and use PyAI Hear for speech-to-text and PyAI Speak for text-to-speech. Your framework keeps control of transport, the LLM, tools, and pipeline behavior.

When should I use Pipecat with PyAI instead of Omni?

Use Pipecat with PyAI when explicit frame processors, custom transports, branching, or per-stage middleware are core requirements.

When should I use PyAI Omni?

Use Omni when you want one managed speech-to-speech agent with turn-taking, knowledge, tools, optional managed telephony, and caller continuity when an Agent profile has it enabled and a caller key is available.

What changes in my code?

Keep your existing framework application. Replace its STT and TTS components with the PyAI services, set PYAI_API_KEY on the worker, and leave your transport, LLM, tools, and business logic in place.

How does pricing work?

$0.001/min for Hear and $0.04/min for Speak when used as components. Omni is $0.05/min*. *Managed telephony is $0.01/min separately. The Pipecat framework is open source. Self-hosting, Pipecat Cloud, transports, and model services have their own operating or usage costs.

Does this page claim one framework is faster?

No. End-to-end behavior depends on the transport, hosting region, LLM, turn settings, and every processor in the pipeline. Test both paths on the same calls and publish the conditions with any result.

Pick your control boundary. Keep the speech layer.

Use PyAI Hear and Speak inside Pipecat, or run the complete agent on Omni.

Get API Key