← back to the directory
Library / SDK Agents & Orchestration

Pipecat

1Framework 2for 3real-time 4voice 5AI 6agents.

the six Ws · specification

W1 Who

Open-source project from Daily.

W2 What

Builds real-time voice and multimodal agents.

W3 Where

A Python library, self-hosted or cloud.

W4 When

When building spoken, low-latency conversations.

W5 Why

Handles streaming audio, turn-taking, and pipelines.

W6 With

Speech and LLM provider APIs.

PythonVoiceReal-time

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.