Back to appsSubmit
WhisperLive---GPU

WhisperLive---GPU

Docker app from grtgbln's Repository

Overview

A real-time transcription application that uses the OpenAI Whisper model to convert speech input into text output. It can be used to transcribe both live audio input from microphone and pre-recorded audio files.
This version runs on an Nvidia GPU.

Requirements


        The image for this container is quite large.
    

Runtime arguments

Web UI
http://[IP]:[PORT:9090]/
Network
bridge
Privileged
false
Extra Params
--runtime=nvidia --gpus all

Template configuration

API PortPorttcp

Container Port: 9090

Target
9090
Default
9090
Value
9090

Categories

AIProductivityTools > UtilitiesOther

Links

TemplateSupportGHCRProject

Details

Repository
ghcr.io/collabora/whisperlive-gpu:latest
Registry
https://registry.hub.docker.com/r/ghcr.io/collabora/whisperlive-gpu
Last Updated2026-06-01
First Seen2025-05-03

Run WhisperLive---GPU on Unraid.

WhisperLive---GPU is listed in Community Apps for Unraid OS. Explore Unraid to build a flexible home server, NAS, or homelab.

Explore Unraid OS