Packages
Python wrapper for Intel RealSense SDK 2.0 that enables depth and color streaming from RealSense depth cameras, with access to calibration data and frame intrinsics.
Integrates Speechmatics speech-to-text into LiveKit Agents, enabling real-time transcription with optional speaker diarization and configurable turn detection modes.
Install it if you are building a LiveKit agent and need Speechmatics transcription with speaker diarization or flexible turn detection.
Extracts detailed metadata from media files (video, audio, container format, codecs, bitrates, resolution, language) via CLI or Python API using pluggable backends like MediaInfo, FFmpeg, or MKVToolNix.
Install it if you need to programmatically inspect video or audio files.
OpenTimelineIO provides an interchange format and Python API for representing and manipulating editorial timeline information—the order, length, and timing of cuts—without storing media itself.
OpenImageIO reads, writes, and processes images in nearly any file format via a format-agnostic API, with support for VFX-production image types including EXR, TIFF, JPEG, PNG, and many others through a plugin architecture.
Implements Widevine Content Decryption Module (CDM) functionality in Python, enabling license acquisition and key retrieval for DRM-protected content.
However, the GPL-3.0 copyleft license is a hard blocker for proprietary projects, and you must obtain a Google-provisioned device provision separately—the package…
Norfair adds real-time multi-object tracking to any detector by matching detected coordinates across frames using configurable distance functions and Kalman filtering.
Install it if you need real-time multi-object tracking in video and already have a detector.
Read, write, and modify Advanced Authoring Format (AAF) files used in video editing and media production, with support for embedding media and copying objects between files.
However, be aware that maintenance is dormant—last release was over a year ago—so if you encounter format compatibility issues with newer AAF variants or need active…
Whisker is a real-time debugger for Pipecat voice and multimodal AI applications that lets you inspect workers, pipelines, jobs, and message flow across a multi-agent system through a graphical UI.
Python ctypes-based interface to the mpv media player, exposing mpv's API for programmatic control of video and audio playback.
However, the 476-day release gap and known macOS event-handling issues warrant checking current compatibility with your mpv version and target platform before…
DocArray provides a Python data structure for representing, transmitting, storing, and retrieving multimodal data, with built-in support for tensors from NumPy, PyTorch, TensorFlow, and JAX.
Subliminal downloads subtitles for video files from multiple online providers, available as both a command-line tool and a Python library.
Install it if you regularly need to download subtitles for video files.
Integrates Telnyx telephony services with LiveKit Agents, enabling voice agents to make and receive phone calls through the Telnyx network.
Provides a lightweight, ready-to-use web UI for testing and debugging Pipecat transports without building a custom client implementation.
pypylon is the official Python binding for Basler pylon C++ APIs, enabling control and image acquisition from Basler machine vision cameras and supporting image processing via the pylon Data Processing API.
Parses track names and filenames to extract language, codec, and accessibility metadata (SDH, closed captions, forced subtitles, commentary) for audio and subtitle streams.
Install it if you work with video files that need track-level metadata enrichment or language variant detection.
A Python wrapper around FFmpeg with full type hints and IDE autocomplete support, letting you build video and audio processing pipelines with compile-time type checking.
Integrates Gladia's speech-to-text API with LiveKit Agents, enabling streaming transcription with multi-language support, code-switching, interim results, and optional real-time translation.
Install it if you are building a LiveKit Agents application and need Gladia's speech-to-text capabilities; it is the intended integration point for that use case.
Integrates Sarvam.ai's Indian-language voice AI services (speech-to-text, text-to-speech, and LLM chat) into LiveKit Agents for real-time conversational applications.
Jina is a framework for building and deploying AI services that communicate via gRPC, HTTP, and WebSockets, with built-in support for scaling, containerization, and cloud deployment.
Not recommended if you prefer minimal dependencies or need cutting-edge feature velocity.
Provides a ready-to-use WebRTC client UI for testing and prototyping SmallWebRTCTransport implementations, mountable directly into FastAPI applications.
Not recommended for production use without evaluation of whether the prebuilt client meets your specific requirements.
Integrates Inworld's text-to-speech and speech-to-text APIs into LiveKit voice agents, enabling real-time voice synthesis and transcription for conversational AI applications.
Anam plugin for the LiveKit Agents framework that extends voice agent capabilities with additional speech processing or model integration features.
However, verify that anam's functionality aligns with your use case before committing, as its exact role in the agent pipeline is not clearly documented in the…