🎙️ Pipecat: Real-Time Voice & Multimodal AI Agents

Pipecat is an open-source Python framework for building real-time voice and multimodal conversational agents. Orchestrate audio and video, AI services, different transports, and conversation pipelines effortlessly—so you can focus on what makes your agent unique.

🚀 What You Can Build

• Voice Assistants – natural, streaming conversations with AI
• 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

🧭 Looking to build structured conversations? Check out Pipecat Flows for managing complex conversational states and transitions.

🧠 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
• Real-Time: Ultra-low latency interaction with different transports (e.g. WebSockets or WebRTC)

🎬 See it in action

 
 

📱 Client SDKs

You can connect to Pipecat from any platform using our official SDKs:

Platform	SDK Repo	Description
Web	pipecat-client-web	JavaScript and React client SDKs
iOS	pipecat-client-ios	Swift SDK for iOS
Android	pipecat-client-android	Kotlin SDK for Android
C++	pipecat-client-cxx	C++ client SDK

🧩 Available services

Category	Services
Speech-to-Text	AssemblyAI, Azure, Deepgram, Fal Wizper, Gladia, Google, Groq (Whisper), OpenAI (Whisper), Parakeet (NVIDIA), Ultravox, Whisper
LLMs	Anthropic, Azure, Cerebras, DeepSeek, Fireworks AI, Gemini, Grok, Groq, NVIDIA NIM, Ollama, OpenAI, OpenRouter, Perplexity, Qwen, Together AI
Text-to-Speech	AWS, Azure, Cartesia, Deepgram, ElevenLabs, FastPitch (NVIDIA), Fish, Google, LMNT, Neuphonic, OpenAI, Piper, PlayHT, Rime, XTTS
Speech-to-Speech	Gemini Multimodal Live, OpenAI Realtime
Transport	Daily (WebRTC), FastAPI Websocket, SmallWebRTCTransport, WebSocket Server, Local
Video	Tavus, Simli
Memory	mem0
Vision & Image	fal, Google Imagen, Moondream
Audio Processing	Silero VAD, Krisp, Koala, Noisereduce
Analytics & Metrics	Canonical AI, Sentry

📚 View full services documentation →

⚡ Getting started

You can get started with Pipecat running on your local machine, then move your agent processes to the cloud when you’re ready.

# Install the module
pip install pipecat-ai

# Set up your environment
cp dot-env.template .env

To keep things lightweight, only the core framework is included by default. If you need support for third-party AI services, you can add the necessary dependencies with:

pip install "pipecat-ai[option,...]"

🧪 Code examples

• Foundational — small snippets that build on each other, introducing one or two concepts at a time
• Example apps — complete applications that you can use as starting points for development

🛠️ Hacking on the framework itself

1. Set up a virtual environment before following these instructions. From the root of the repo:

   python3 -m venv venv
   source venv/bin/activate

2. Install the development dependencies:

   pip install -r dev-requirements.txt

3. Install the git pre-commit hooks (these help ensure your code follows project rules):

   pre-commit install

4. Install the pipecat-ai package locally in editable mode:

   pip install -e .

   The -e or --editable option allows you to modify the code without reinstalling.

5. Include optional dependencies as needed. For example:

   pip install -e ".[daily,deepgram,cartesia,openai,silero]"

6. (Optional) If you want to use this package from another directory:

   pip install "path_to_this_repo[option,...]"

Running tests

From the root directory, run:

pytest

Setting up your editor

This project uses strict PEP 8 formatting via Ruff.

Emacs

You can use use-package to install emacs-lazy-ruff package and configure ruff arguments:

(use-package lazy-ruff
  :ensure t
  :hook ((python-mode . lazy-ruff-mode))
  :config
  (setq lazy-ruff-format-command "ruff format")
  (setq lazy-ruff-check-command "ruff check --select I"))

ruff was installed in the venv environment described before, so you should be able to use pyvenv-auto to automatically load that environment inside Emacs.

(use-package pyvenv-auto
  :ensure t
  :defer t
  :hook ((python-mode . pyvenv-auto-run)))

Visual Studio Code

Install the Ruff extension. Then edit the user settings (Ctrl-Shift-P Open User Settings (JSON)) and set it as the default Python formatter, and enable formatting on save:

"[python]": {
    "editor.defaultFormatter": "charliermarsh.ruff",
    "editor.formatOnSave": true
}

PyCharm

ruff was installed in the venv environment described before, now to enable autoformatting on save, go to File -> Settings -> Tools -> File Watchers and add a new watcher with the following settings:

1. Name: Ruff formatter
2. File type: Python
3. Working directory: $ContentRoot$
4. Arguments: format $FilePath$
5. Program: $PyInterpreterDirectory$/ruff

🤝 Contributing

We welcome contributions from the community! Whether you're fixing bugs, improving documentation, or adding new features, here's how you can help:

• Found a bug? Open an issue
• Have a feature idea? Start a discussion
• Want to contribute code? Check our CONTRIBUTING.md guide
• Documentation improvements? Docs PRs are always welcome

Before submitting a pull request, please check existing issues and PRs to avoid duplicates.

We aim to review all contributions promptly and provide constructive feedback to help get your changes merged.

🛟 Getting help

➡️ Join our Discord

➡️ Read the docs

➡️ Reach us on X