# WhisperLive CPU

WhisperLive CPU is a self-hosted ai app. A real-time transcription application that uses the OpenAI Whisper model to convert speech input into text output. It is open source and self-hosted, installable on Unraid.

Canonical page: https://ourlocalhost.com/app/3478/whisperlive-cpu

## Description

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 a microphone and pre-recorded audio files. This version runs on CPU.

## Platform availability

Available on 1 of 10 platforms: Unraid.

## Health score

79/100 (Good), based on 5 of 5 factors.
- Maintained: 100 (last commit 5 days ago)
- Popular: 73 (4,361 GitHub stars)
- Easy to install: 35 (1 install platform, install notes, Docker image)
- Light to run: 70 (700 MB minimum RAM)
- Security check: 95 (no serious findings, CI, tests)

## Links

- Unraid: https://ca.unraid.net/apps/whisperlive-cpu-0mstbkd12lf021?q=WhisperLive---CPU

## Common questions

### Can WhisperLive transcribe pre-recorded audio files?

Yes, it can transcribe live audio input from a microphone and pre-recorded audio files.

### Which backends does WhisperLive support?

It supports multiple backends, including faster_whisper, tensorrt, and openvino.

### Is there a Docker install path for self-hosting WhisperLive---CPU?

Yes, the project page provides a Docker install guide for self-hosting WhisperLive---CPU.

### Where can I report bugs for WhisperLive?

Report bugs in the collabora/WhisperLive GitHub issue tracker.

---
Source: Our Local Host (https://ourlocalhost.com/app/3478/whisperlive-cpu), the self-hosted and open-source app directory.
