Pipecat
Open-source framework for real-time voice and multimodal AI agents
About
Python framework for building real-time voice and multimodal conversational agents. Handles the full low-latency pipeline — STT → LLM → TTS — with 40+ provider integrations. The most developer-friendly OSS option for building production voice agents where you need code-level control.
Choose Pipecat when…
- •You want code-level control over your full voice agent pipeline
- •You're building real-time multimodal agents that handle voice and vision together
- •You need to mix and match STT, LLM, and TTS providers freely
Builder Slot
Speech synthesis and recognition APIs — text-to-speech, speech-to-text, and real-time audio intelligence
Other tools in this slot:
Stack Genome Detection
AIchitect's Genome scanner detects Pipecat in your project via these signals:
pipecat-aiIntegrates with (2)
Pipecat ships a Deepgram STT service that streams audio frames in and transcribed text out as a pipeline node.
→ Drop Deepgram STT into a Pipecat voice agent pipeline with a single service binding.
Pipecat ships an ElevenLabs TTS service that turns the model's text output into streaming audio frames for the user.
→ Drop ElevenLabs TTS into a Pipecat voice agent pipeline with a single service binding.
Alternatives to consider (2)
Pricing
Recent Activity
Crossed 10,000 stars ⭐
3 weeks ago
Crossed 5,000 stars ⭐
3 weeks ago
Crossed 1,000 stars ⭐
3 weeks ago
In 1 stack
Ruled out by 1 stack
Badge
Add to your GitHub README
[](https://www.aichitect.dev/tool/pipecat)Explore the full AI landscape
See how Pipecat fits into the bigger picture — browse all 207 tools and their relationships.