# Pipecat

> Updated 2026-08-26 · type: tool · category: ai-infrastructure · status: active · rev 1

Open-source framework for real-time voice agents, multimodal apps, and live AI — composable pipelines with swappable STT (22+), TTS (35+), any LLM, and…

- Open source: yes (BSD-2-Clause)
- Self-hostable: yes
- Pricing: self-host free (BSD-2); Pipecat Cloud usage-based, agent-1x from $0.01/min active or $0.0005/min reserved
- Best for: Developers building real-time voice and multimodal conversational AI agents in Python.
- Last verified: 2026-09-04

- **Canonical:** https://gtmstacker.com/registry/tool/pipecat/
- **Source:** [github · pipecat-ai/pipecat](https://github.com/pipecat-ai/pipecat)
- **Tags:** ai-infrastructure, voice-ai, realtime, framework
- **Repository:** https://github.com/pipecat-ai/pipecat

## Is Pipecat open source?

Yes — BSD-2-Clause-licensed.

## How much does Pipecat cost?

self-host free (BSD-2); Pipecat Cloud usage-based, agent-1x from $0.01/min active or $0.0005/min reserved (usage).

## Can I self-host Pipecat?

Yes — it can be self-hosted.


---

Open-source framework for real-time voice agents, multimodal apps, and live AI — composable pipelines with swappable STT (22+), TTS (35+), any LLM, and WebRTC/WebSocket/Twilio/WhatsApp transports, plus multi-agent composition and sub-200ms latency. Maintained by Daily.

## Provenance

- BSD-2-Clause independently verified (15.2k★, active). `pipecat init` scaffolds a runnable bot; ships Claude Code skills.
- Surfaced via the GTM Stacker X/Twitter signal reports (Aug–Sep 2026); license independently WebFetch-verified 2026-09-03.