LiveKit Agents

by LiveKit

Open-source framework for building realtime AI voice agents on LiveKit's WebRTC stack.

TL;DR

Open-source framework for building realtime AI voice agents on LiveKit's WebRTC stack.

Best for teams already on LiveKit WebRTC that want to add a realtime AI participant. Pricing: free.

Category
Open source
License
—
Stars
—
Last push
—
Pricing
free
Platforms
Linux, macOS, Windows, Cloud

What it is

LiveKit Agents is an Apache-2.0 framework that runs an AI participant inside a LiveKit room with realtime audio. It plugs into OpenAI Realtime, Deepgram, Cartesia, ElevenLabs, and Anthropic via provider abstractions, handling turn detection, interruption, and tool calling. OpenAI references LiveKit Agents in its own Realtime API docs.

Best for: Teams already on LiveKit WebRTC that want to add a realtime AI participant.
Watch out for: Tightly coupled to LiveKit transport; you still pay for ASR/LLM/TTS providers.

Install / use

pip install livekit-agents

Features

Speaker diarizationNo
Word-level timestampsNo
Streaming / real-timeNo
Languages supportedNone
HIPAA eligibleNo

LiveKit Agents vs Whipscribe

FeatureLiveKit AgentsWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarization—Yes
Word timestamps—Yes
Streaming—No
Languages—99
PlatformsLinux, macOS, Windows, CloudWeb, API, MCP

Alternatives to LiveKit Agents

OpenAI Whisper
OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 98.1k
whisper.cpp
Georgi Gerganov

C/C++ port of Whisper — runs on anything, from a Raspberry Pi to Apple Silicon.

OSS · MIT ★ 48.8k
faster-whisper
SYSTRAN

4× faster than reference Whisper using CTranslate2 — production sweet spot.

OSS · MIT ★ 22.3k

Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.