Pipecat

What it does

Pipecat is an open source ecosystem, maintained by Daily, for building voice and multimodal AI agents. Developers build a Python pipeline that coordinates voice, video, text and images, connect it to a transport such as WebRTC, SIP or PSTN, and stream frames through each stage as they are produced. Client SDKs cover web and mobile so end users can connect from a browser, app or phone.

Teams compose pipelines, swap speech, language and vision services with a one-line change, add tools and subagents, and observe runs with metrics, traces and OpenTelemetry. The pipecat init command scaffolds a runnable project and registers the Context Hub MCP server so a coding agent can use current Pipecat APIs. Interruption handling and turn detection help conversations feel natural.

Pipecat suits developers and enterprise teams taking real-time voice agents to production. The framework is free under the BSD-2 license and you pay only for the services you choose. Self-hosting runs wherever Python runs, while Pipecat Cloud and Enterprise are hosted options with pricing available from the vendor.

What it can do

• Orchestrate voice, video, text and image inputs in one real-time pipeline
• Swap speech, language and vision services from 200+ integrated providers
• Handle interruptions, turn detection and conversation context
• Hand off to subagents and follow defined conversation paths with Pipecat Flows
• Connect over WebRTC, SIP and PSTN transports with client SDKs and UI kit
• Observe runs with metrics, traces and OpenTelemetry

Works with

• Soniox
• OpenAI
• Cartesia
• Daily

Before you choose

• The framework is free under BSD-2, but you pay the AI service and hosting providers you choose.
• Pipecat Cloud and Enterprise pricing should be confirmed with Daily sales.
• Real-time voice performance depends on the chosen transport, models and deployment environment.

Listed under

• Coding
• MCP and agent tools
• AI agents
• Developer tools
• Multimodal
• Open source
• Python framework
• Real-time

Get started

Run uv add pipecat-ai, then follow the quickstart guide.

1. Install the framework with uv add pipecat-ai.
2. Run pipecat init to scaffold a project and register the Context Hub MCP server.
3. Follow the Quickstart to build a first voice bot, then connect a client SDK.

The open source framework is free to use under BSD-2, and you pay for any AI services and hosting you choose. Verify Pipecat Cloud and Enterprise rates with Daily.

We couldn’t find published prices for Pipecat. See their pricing page ↗

Sources for this overview

Product pages, documentation, and pricing checked 30 Oct 2026. Each source supports part of the overview; availability and prices can change.

• Pipecat Documentation - Pipecat ↗docs.pipecat.ai
• Pipecat ↗www.pipecat.ai
• Pipecat ↗www.pipecat.ai

Company website

pipecat.ai: product, pricing and policy pages

YC directory mirror

Batch and company name

Web search

Confirms the official site

Social accounts

Accounts the company links, and its posts on X

Human review

Checked by a person

knowledge_base

manual_review

Last checked 30 Oct 2026. Every field keeps its source and date; unknown means we couldn’t confirm it.