---
title: Whishper Self-Hosted Speech-to-Text and Audio Workflow Skill
slug: whishper-self-hosted-speech-to-text-audio-workflow-skill
description: Whishper is an open source self-hosted web app for speech-to-text, translation, and subtitle workflows built around Whisper models. This skill covers running Whishper with Docker, handling uploads and transcripts, and wiring the output into broader automation flows.
github_stars: 2974
verification: security_reviewed
source: https://github.com/pluja/whishper
category: Media & Transcription
framework: Multi-Framework
tool_ecosystem:
  github_repo: pluja/whishper
  github_stars: 2974
---
# Whishper Self-Hosted Speech-to-Text and Audio Workflow Skill

Whishper is an open source self-hosted web app for speech-to-text, translation, and subtitle workflows built around Whisper models. This skill covers running Whishper with Docker, handling uploads and transcripts, and wiring the output into broader automation flows.

## Installation

1. Clone this skill repository.
2. Open this skill folder.
3. Review prerequisites and setup needs.
4. Install required dependencies.
5. Run and test in your environment.

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/whishper-self-hosted-speech-to-text-audio-workflow-skill/)