1fe8cf5289
Decouple context management from turn frames and transcripts when a
realtime LLM service drives the conversation. Three problems with today's
behavior:
- Some realtime services (Gemini Live, AWS Nova Sonic, Ultravox) emit
no UserStarted/StoppedSpeakingFrame at all, so the aggregator — which
writes user messages on those frames — doesn't write to context
correctly without them.
- The workaround (local VAD on the aggregator) generates turn
boundaries that don't match the provider's server-side ground truth,
and the per-service "do I need it?" rule is hard to keep straight.
- When local turn detection is the intended driver, turn-end strategies
still wait for transcripts on the latency critical path.
Add a realtime_service_mode: RealtimeServiceModeConfig | None = None
kwarg on LLMContextAggregatorPair. When set, the pair switches both
halves to trailing context writes: user messages are flushed on the first
assistant content frame, assistant messages on the next user transcript,
both halves on EndFrame. Turn-end strategies stop waiting for transcripts
by default. Two fine-grained boolean fields (context_writes_await_turns,
turns_await_transcripts) let callers dial back to cascade-style behavior
selectively; their invalid combination is rejected in __post_init__.
The bifurcation is dispatch-only: seven branch points across the two
halves, each at method entry, each delegating to a mode-pure private
method. Cross-half coordination uses an asyncio.Lock and a back-reference
shared by both halves; the assistant signals user.flush() on
LLMFullResponseStartFrame, and the user signals assistant.flush() on the
first new transcript after the assistant turn. The mechanism reuses the
existing push_aggregation() — no parallel write path.
Two new events fire when messages are flushed to context:
on_user_message_added and on_assistant_message_added. In cascade mode
they coincide with the existing turn-stopped events; in realtime mode
(where the turn-stopped event fires before the message is finalized)
they're the canonical way to subscribe to "context just updated, here's
the text."
UserTurnStoppedMessage.content is now typed str | None to reflect that
realtime mode fires the event with None.
When a RealtimeServiceMetadataFrame arrives and realtime_service_mode is
None, the aggregator logs a one-time INFO recommendation pointing users
at the option.
🎙️ 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.
Want to dive right in? Run
pipecat init quickstartor follow the quickstart guide.
🚀 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
🧠 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)
🌐 Pipecat Ecosystem
🧩 Multi-agent systems
Need multiple AI agents working together? Pipecat Subagents lets you build distributed multi-agent systems where each agent runs its own pipeline and communicates through a shared message bus. Hand off conversations between specialists, dispatch background tasks, and scale agents across processes or machines.
📱 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
Looking to build structured conversations? Check out Pipecat Flows for managing complex conversational states and transitions.
🪄 Beautiful UIs
Want to build beautiful and engaging experiences? Checkout the Voice UI Kit, a collection of components, hooks and templates for building voice AI applications quickly.
🛠️ Create and deploy projects
Create a new project in under a minute with the Pipecat CLI. 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.
🧩 Community Integrations
Build and share your own Pipecat service integrations! Browse existing community integrations or check out our guide to create your own.
📺️ Pipecat TV Channel
Catch new features, interviews, and how-tos on our Pipecat TV channel.
🎬 See it in action
🧩 Available services
📚 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 uv
curl -LsSf https://astral.sh/uv/install.sh | shNeed help? Refer to the uv install documentation.
-
Install the module
# For new projects uv init my-pipecat-app cd my-pipecat-app uv add pipecat-ai # Or for existing projects uv add pipecat-ai -
Set up your environment
cp env.example .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:
uv add "pipecat-ai[option,...]"
Using pip? You can still use
pip install pipecat-aiandpip install "pipecat-ai[option,...]"to get set up.
🧪 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
🛠️ Contributing to the framework
Prerequisites
Minimum Python Version: 3.11 Recommended Python Version: >= 3.12
Setup Steps
-
Clone the repository and navigate to it:
git clone https://github.com/pipecat-ai/pipecat.git cd pipecat -
Install development and testing dependencies:
uv sync --group dev --all-extras \ --no-extra gstreamer \ --no-extra local \ -
Install the git pre-commit hooks:
uv run pre-commit install
Note
: Some extras (local, gstreamer) require system dependencies. See documentation if you encounter build errors.
Claude Code Skills
Install development workflow skills for contributing to Pipecat with Claude Code:
claude plugin marketplace add pipecat-ai/pipecat
claude plugin install pipecat-dev@pipecat-dev-skills
Running tests
To run all tests, from the root directory:
uv run pytest
Run a specific test suite:
uv run pytest tests/test_name.py
🤝 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.