pipecat-ai
An open source framework for voice (and multimodal) assistants
Decision gist · record as of 2026-08-14
Yes. Pipecat is actively maintained, permissively licensed, has low install friction, and solves a real problem (real-time multimodal agent orchestration) that would otherwise require gluing together many libraries. The 14k GitHub stars and recent release cycle signal maturity and community adoption. No known vulnerabilities. Install if you're building voice or multimodal agents; skip if you only need simple speech-to-text or text-to-speech without orchestration.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.11 or later.
- Some audio/video features may require system libraries (e.g., for audio encoding/decoding via onnxruntime and soxr).
- Low install friction with a pure-Python wheel.
License · maintenance · safety
BSD-2-Clause (permissive) — BSD-2-Clause (permissive) allows commercial use, modification, and distribution with minimal restrictions—suitable for proprietary projects as long as you include the license and original copyright notice.
last release 2026-08-01 (13 days) · last repo commit 2026-08-14 · 14,114 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 1,228,728 downloads/mo, #4,189 on PyPI
Alternatives
Verify before relying
pip install pipecat-ai
from pipecat.core.pipeline import Pipeline
from pipecat.services.openai import OpenAILLMService
# Build a simple voice agent pipeline
pipeline = Pipeline()
pipeline.add_service(OpenAILLMService())- Whether all 22 runtime dependencies are required for basic voice agent use or if subsets are optional.
- Specific system-level audio/video codec requirements beyond Python packages.
- Real-world latency characteristics for different transport types (WebSocket vs WebRTC).
- Whether the framework supports local-only operation or requires cloud AI services.
What it is and what it does
Pipecat is a framework for building conversational AI agents that handle voice and video in real-time. It abstracts the complexity of orchestrating speech recognition, text-to-speech, LLM calls, and media transport so you can focus on agent logic. The framework supports single agents or multi-agent systems where agents can hand off work, run in parallel, or coordinate over a shared bus—all on a single machine or distributed across processes and servers.
You compose agents from modular pipeline components: audio/video sources, AI services (speech-to-text, language models, text-to-speech), and transports (WebSocket, WebRTC). The framework handles streaming, buffering, and synchronization. It integrates with services like OpenAI and supports pluggable backends for speech and LLM providers. The ecosystem includes client SDKs for web and mobile, a CLI for scaffolding and deployment, and debugging tools.
Use it for
- Build voice assistants with natural streaming conversations, speech recognition, and real-time text-to-speech responses.
- Create multi-agent systems where specialist agents hand off tasks, fan out in parallel, or run as sidecars coordinating over a shared bus.
- Develop AI companions (coaches, meeting assistants, characters) with voice and video interaction.
- Build business agents for customer intake, support bots, or guided conversation flows.
- Create interactive storytelling or creative tools that generate voice and video responses.
- Design complex dialog systems with structured conversation paths and state management using Pipecat Flows.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
Pipecat is actively maintained, permissively licensed, has low install friction, and solves a real problem (real-time multimodal agent orchestration) that would otherwise require gluing together many libraries. The 14k GitHub stars and recent release cycle signal maturity and community adoption. No known vulnerabilities. Install if you're building voice or multimodal agents; skip if you only need simple speech-to-text or text-to-speech without orchestration.
Install
pipecat-ai on PyPI
Before you install
Low install friction with a pure-Python wheel. Active maintenance with a recent release (13 days ago) and strong community engagement (14114 GitHub stars). Requires Python 3.11+. The 22 runtime dependencies are substantial but standard for audio/video/AI work (numpy, protobuf, onnxruntime, openai, websockets, etc.).
Requires Python 3.11 or later. Some audio/video features may require system libraries (e.g., for audio encoding/decoding via onnxruntime and soxr).
License in practice
BSD-2-Clause (permissive) allows commercial use, modification, and distribution with minimal restrictions—suitable for proprietary projects as long as you include the license and original copyright notice.
Quickstart
pip install pipecat-ai
from pipecat.core.pipeline import Pipeline
from pipecat.services.openai import OpenAILLMService
# Build a simple voice agent pipeline
pipeline = Pipeline()
pipeline.add_service(OpenAILLMService())Verify before relying
- Whether all 22 runtime dependencies are required for basic voice agent use or if subsets are optional.
- Specific system-level audio/video codec requirements beyond Python packages.
- Real-world latency characteristics for different transport types (WebSocket vs WebRTC).
- Whether the framework supports local-only operation or requires cloud AI services.
Package facts
| License | BSD-2-Clause permissive |
| Python support | Supports the current Python release >=3.11 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 22 packagesaiofilesaiohttpaudioop-ltsdocstring_parserloguruMarkdownnltknumpyPillowprotobufpydanticpyloudnormresampysoxropenaityping_extensionsnumbawait_for2websocketspyyamlnum2wordsonnxruntime |
| Maintenance | Actively maintained 13 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 1,228,728 / month, #4,189 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 5 - Production/StableIntended Audience :: DevelopersTopic :: Communications :: ConferencingTopic :: Multimedia :: Sound/AudioTopic :: Multimedia :: VideoTopic :: Scientific/Engineering :: Artificial Intelligence |
Evidence: pipecat_ai-1.7.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “multimodal conversational ai framework”
- pipecat-aiPipecat is a Python framework for building real-time voice and…
- pipecat-ai-whiskerWhisker is a real-time debugger for Pipecat voice and multimodal AI…
- reka-apiProvides a Python client library for accessing the Reka API, with…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also daily-python · pipecat-ai-flows · pipecat-ai-whisker · pipecatcloud · pipecat-ai-prebuilt · pipecat-ai-small-webrtc-prebuilt · rasa · livekit-plugins-assemblyai · livekit-plugins-anthropic · camel-ai