pipecat-ai /pipecat
Open Source framework for voice agents, multimodal apps, and realtime AI. Maintained by Daily and the community.
★ 17,271⑂ 3,117👁 85⑃ 5,321● 1,482▤ 126
+10
日增长
17,271
stars
3,117
forks
85
watchers
5,321
prs
1,482
issues
126
releases
README
!Tests 🎙️ Pipecat: Real-Time Voice & Multimodal AI Agents Pipecat is an open-source Python framework for building real-time voice and multimodal conversational agents. Build a single voice agent or a full multi-agent system where specialists hand off, fan out in parallel, and coordinate over a shared bus, locally or distributed across processes and machines. Orchestrate audio and video, AI services, transports, and conversation pipelines effortlessly, so you can focus on what makes your agents unique. Want to dive right in? Run pipecat init quickstart or follow the quickstart guide. 🚀 What you can build - Voice Assistants – natural, streaming conversations with AI - Multi-Agent Systems – specialists that hand off, fan out in parallel, or run as sidecars over a shared bus - AI Companions – coaches, meeting assistants, characters - Multimodal Interfaces – voice, video, images, and more - Interactive Storytelling – creative tools with generative media - Business Agents – customer intake, support bots, guided flows - Complex Dialog Systems – design logic with structured conversations 🧠 Why Pipecat? - Voice-first: Integrates speech recognition, text-to-speech, and conversation handling - Pluggable: Supports many AI services and tools - Composable Pipelines: Build complex behavior from modular components - Multi-Agent Ready: Each pipeline is an agent. Compose them with handoff, parallel fan-out, sidecar workers, or distributed deployments - Real-Time: Ultra-low latency interaction with different transports (e.g. WebSockets or WebRTC) 🌐 Pipecat ecosystem 📱 Client SDKs Building client applications? You can connect to Pipecat from any platform using our official SDKs: JavaScript | React | React Native | Swift | Kotlin | C++ | ESP32 🧭 Structured conversations Need predefined or dynamic conversation paths with state management? Pipecat Flows is built into Pipecat. Browse the examples to see it in action. 🪄 Beautiful UIs Want to build beautiful and engaging experiences? Check out Pipecat UI, a shadcn registry of components for building voice AI applications. Browse the documentation for component previews and installation guides. 🛠️ Create and deploy projects The Pipecat CLI ships with pipecat-ai — install it with uv tool install "pipecat-ai[cli]". Run pipecat init to start a project: it sets you up so an AI coding assistant (Claude Code, Codex) builds it for you, and can scaffold a runnable bot in under a minute. Then use the CLI to monitor and deploy your agent to production. 🔍 Debugging Looking for help debugging your pipeline and processors? Check out Whisker, a real-time Pipecat debugger. 🖥️ Terminal Love terminal applications? Check out Tail, a terminal dashboard for Pipecat. 🤖 Claude Code skills Use Pipecat Skills with Claude Code to scaffold projects, deploy to Pipecat Cloud, and more. Install the marketplace with: claude plugin marketplace add pipecat-ai/skills and install any of the available plugins. 🧩
Top issues
#3989Allow excluding specific messages from context summarization9 comments · 2026-03-11#1015Add WordTTSService support for aws PollyTTSService9 comments · 2025-01-16#5683TranscriptionFrame queued behind the frame that starts a user turn is dropped by that turn's own interruption7 comments · 2026-09-10#6110AnthropicLLMService: after a tool or system prompt change, every later request fails with a 400 on accounts with preserved thinking enforced6 comments · 2026-10-11#4996Interruption loses played TTS text from assistant context (InterruptionFrame overtakes released TTSTextFrames + transport queue drop) — bot repeats itself6 comments · 2026-07-10#3985Proposal: graceful interruption release for TTS/output transports6 comments · 2026-03-11#2811Option to Initiate Outbound Whatsapp Business Call6 comments · 2025-10-08#1882Support for combined STT + LLM with gpt4o-audio-preview6 comments · 2025-05-24
Latest release
v1.16.0 v1.16.0 2026-11-12Added
- Added a normalization field to CartesiaTTSService.Settings and CartesiaHttpTTSService.Settings, passing Cartesia's text normalization mode ("auto", "off", or a locale code such as "en-GB") through to synthesis requests.
(PR 5430)
- Added SarvamHttpSTTService, which sends each VAD speech segment to Sarvam's REST speech-to-text API (saaras:v4 by default, or saaras:v3) and yields the transcription from run_stt(). It takes the same mode and keyterms options as SarvamSTTService, and sends a segment longer than the API's 30-second limit as consecutive pieces whose transcripts are joined.