Subcategories
Packages
Integrates Azure AI services, particularly Azure Speech, into LiveKit Agents for real-time voice and audio processing in agent applications.
A Python SDK for building video and audio calling into desktop and server applications, with support for joining meetings, managing participants, and sending/receiving media streams.
Install only if your application targets Python 3.8+ and your deployment environment meets the glibc requirement.
spotDL downloads songs from Spotify playlists on YouTube, embedding album art, lyrics, and metadata into the files.
Install it if offline Spotify access is your goal; skip it if you need lossless audio or have legal concerns about YouTube-sourced downloads.
Wraps libsamplerate (Secret Rabbit Code) to perform high-quality audio sample rate conversion using three APIs: Simple, Full, and Callback.
Integrates xAI's Grok LLM with LiveKit's Agent Framework to enable voice agents that can understand and respond in real-time conversations.
Provides utilities for reading, modifying, and synthesizing MIDI data in a Python-friendly format, handling note manipulation, tempo estimation, and audio output.
Embeds imperceptible watermarks into audio files and detects them afterward, using neural network-based techniques that survive common audio transformations.
However, the aging maintenance status and lack of recent updates suggest you should verify that the neural network models and robustness claims meet your specific use…
Integrates Soniox speech-to-text and text-to-speech APIs into LiveKit Agents via WebSocket streaming, enabling real-time transcription and speech synthesis in agent applications.
Install it if you are building a LiveKit agent and want to use Soniox for speech services; it is the intended integration point for that use case.
Streamlink extracts video streams from various online services and pipes them into a video player or file, bypassing resource-heavy websites to access streamed content directly.
aubio is a Python wrapper around a C library for music and audio analysis, providing tools to detect onsets, track pitch, identify beats, and extract spectral features from audio files and streams.
Python ctypes-based bindings to libvlc that let you control VLC media playback and access its API from Python code.
Audiomentations applies randomized audio transformations—noise injection, pitch shifting, time stretching, filtering, and distortion—to augment training data for machine learning models that work with audio.
Install it if audio data augmentation is part of your training pipeline.
Calculates Root Mean Square (RMS) values over sliding windows in NumPy arrays using vectorized C code with SIMD acceleration (AVX on x86-64, NEON on ARM).
Finds the minimum and maximum values in a NumPy array using C and SIMD optimizations, delivering faster results than separate NumPy amin and amax calls.
Coqui TTS synthesizes speech from text using deep learning models, supporting over 1100 languages with pretrained weights and tools for training and fine-tuning custom models.
Install it if you want pretrained models out-of-the-box or plan to fine-tune.
Pitch-shifts and time-stretches audio using the Signalsmith Stretch C++ library, working with mono and multichannel audio data.
pylast provides a Python interface to Last.fm and API-compatible music networks like Libre.fm, enabling programmatic access to music data, scrobbling, and user account operations.
Install it if you need to interact with Last.fm or Libre.fm APIs; skip it if you only need local music metadata or don't require scrobbling or online music service…
Integrates Rime speech recognition into LiveKit's agent framework for building real-time voice agents that can hear and respond to users.
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.
Provides a high-level Python interface to PulseAudio's libpulse library for synchronous control of audio devices, sinks, sources, and volume management.
SoCo is a Python library for programmatic control of Sonos speakers over a network, supporting playback, volume, queue management, and speaker grouping.
Manages conversation flows and state machines for Pipecat AI applications, but this package is deprecated—Pipecat Flows is now integrated into pipecat-ai 1.5.0+ under the pipecat.flows namespace.
Silero provides pre-trained text-to-speech models that convert text to natural-sounding speech across multiple languages and voices, with support for SSML markup and automated stress/homograph handling for Russian.
MediaFile reads and writes metadata tags across many audio file formats through a single, format-independent Python interface, wrapping the low-level Mutagen library.
Install it if you need to read or write audio tags programmatically.
SoundCard plays and records audio across Linux, macOS, and Windows using native OS audio libraries (PulseAudio, CoreAudio, WASAPI) without C extensions, exposing a unified Python interface for speaker and microphone access.
Install it if you need speaker/microphone access without C extension overhead.
Plays audio files (MP3, WAV) and URLs from Python with a single function call, with no external Python dependencies and cross-platform support via native OS audio APIs.
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.
Encodes and decodes audio in SILK format, a codec optimized for speech compression, with support for streaming large files through file-like objects.
Install it if your application requires SILK compression or decompression; otherwise, it is not necessary.
TTS is a deep learning library for text-to-speech synthesis that generates spoken audio from text using pretrained models across multiple languages, with support for model training and fine-tuning.
Integrates Telnyx telephony services with LiveKit Agents, enabling voice agents to make and receive phone calls through the Telnyx network.
python-rtmidi provides a Python interface to the RtMidi C++ library for sending and receiving MIDI messages across Windows, macOS, and Linux systems.
Provides a lightweight, ready-to-use web UI for testing and debugging Pipecat transports without building a custom client implementation.
Async Python library for communicating with Sonos devices over WebSocket connections, enabling remote control and audio playback features like audio clips and volume management.
Fetches synchronized lyrics in LRC format for music tracks from multiple online providers, with options for plain text or word-level karaoke formats.
However, be aware that provider breakage is likely without active maintenance—test each provider you rely on before deploying to production.
symusic parses and transforms MIDI and ABC files at note level with C++20-backed speed, exposing vectorized operations like pitch/velocity/time shifts and audio rendering through SoundFonts.
python-osc implements Open Sound Control (OSC) servers and clients in pure Python, supporting UDP and TCP protocols with multiple concurrency models (blocking, threading, forking, asyncio) and a dispatcher-based address-to-callback routing system.
Install it if you need to send or receive OSC messages from Python; the only constraint is a Python 3.10+ requirement.
eyeD3 reads, edits, and displays ID3 metadata tags in MP3 files via both a command-line tool and a Python library.
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.