Pipecat pipecat-ai/pipecat

Open-source Python framework for real-time voice and multimodal agents that plugs together STT, LLM, TTS and transports.

Creator kit + Compare GitHub ↗ Install guide (official) ↗

Pipecat at a glance

Checked 16 Oct 2026

Pipecat (by Daily) orchestrates speech-to-text, LLM, text-to-speech and transport services into real-time voice agents; it does not include its own models. BSD-2-Clause. The official quickstart uses paid Deepgram, OpenAI and Cartesia API keys, but docs list local options: Whisper STT, Ollama LLM, Piper TTS, plus local and WebRTC transports. Python 3.11+. Hardware depends on the services you choose.

Cite this pageRepoQuarry. “Pipecat.” Checked 16 Oct 2026. https://repoquarry.dev/projects/pipecat

How much of ElevenLabs does it replace?

1 of 4 jobs. Framework only; voice quality and cost depend on the STT, LLM and TTS services you plug in.

Speech generation Not covered

Voice cloning Not covered

Speech recognition Not covered

Voice agents Partial replacement

For speech generation, voice cloning, speech recognition, see other ElevenLabs alternatives. You may also need to build an interface, an API server and hosting yourself.

How much of Vapi does it replace?

2 of 2 jobs. Self-hosted framework; phone calls via Twilio, Telnyx, Plivo and other serializers, which you pay separately.

Voice agents Partial replacement

Phone calls (telephony) Partial replacement

Facts, with sources

Every answer links to where we found it. We read the documentation; we did not install it.

Report a correction

QuestionAnswerSourceChecked

Runs on my machine? Yes, runs on your machine; also deployable to Pipecat Cloud Run Pipecat on your local machine, then move your agent processes to the cloud when you're ready. github.com · pipecat#-getting-started ↗ 1d ago

Code licence BSD-2-Clause github.com · LICENSE ↗ 1d ago

Model weights licence No separate model weights; each plugged-in service or model has its own terms github.com · pipecat#-available-services ↗ 1d ago

Commercial use Yes for the framework (BSD-2-Clause); check the licence or terms of each service you plug in github.com · LICENSE ↗ 1d ago

Paid services needed? Quickstart needs Deepgram, OpenAI and Cartesia API keys; documented local alternatives include Whisper STT (Faster Whisper or MLX), Ollama LLM and Piper TTS, so a fully local pipeline is possible No API keys required - Whisper runs entirely locally for complete privacy. docs.pipecat.ai · whisper ↗ 1d ago

Hardware Not documented for the framework; depends on the chosen services Know the answer? —

Operating systems Reviewed Python-framework README, quickstart and local-bot guide document uv-based execution but no server OS support matrix. The separate C++ client's platform list does not verify Python server compatibility docs.pipecat.ai · quickstart.md ↗ today

Setup effort Easy; uv or pip install pipecat-ai with extras per service, Python 3.11+, plus API keys or local services To keep things lightweight, only the core framework is included by default. github.com · pipecat#manual-installation ↗ 1d ago