WhisperLive

by Collabora

Real-time Whisper transcription over WebSockets.

TL;DR

Real-time Whisper transcription over WebSockets.

Best for live captioning, meeting bots, low-latency voice agents on self-hosted GPU. Pricing: free.

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

What it is

Collabora's WebSocket server that pipes microphone audio into faster-whisper with a VAD + streaming decoder. Includes browser, Python, and CLI clients. MIT.

Best for: Live captioning, meeting bots, low-latency voice agents on self-hosted GPU.
Watch out for: Faster-whisper backend → CTranslate2 GPU only; English latency ~300ms, multilingual slower.

Install / use

git clone https://github.com/collabora/WhisperLive

Features

Speaker diarizationNo
Word-level timestampsYes
Streaming / real-timeYes
Languages supported99
HIPAA eligibleNo

WhisperLive vs Whipscribe

FeatureWhisperLiveWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingYesNo
Languages9999
PlatformsLinux, macOS, DockerWeb, API, MCP

Alternatives to WhisperLive

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.