Kabanosk/whisper-website

Simple self-hosted web application, which can be used to convert audio to subtitles by OpenAI's Whisper model

What it solves

It provides a simple, self-hosted interface for converting audio files into text and subtitles without relying on cloud services, ensuring that transcription and translation happen entirely on the user's own machine.

How it works

The application acts as a web-based wrapper for OpenAI's Whisper model. Users upload an audio file via the browser, select a specific Whisper model size (ranging from tiny to large), and the system processes the audio to generate a transcript.

Who it’s for

People who want a private, local alternative to cloud-based transcription services to create subtitles or text transcripts from audio files.

Highlights

  • Local Processing: Everything runs on your own machine with no cloud dependency.
  • Multiple Export Formats: Supports .srt, .vtt, and plain .txt files.
  • Model Flexibility: Allows users to choose between different Whisper model sizes for varying levels of accuracy and speed.
  • Translation: Includes an optional feature to translate the transcript into another language.

Related

  • Project
    olyaiy/resume-lm

    ResumeLM is an open‑source web app that uses LLMs (OpenAI, Claude, Gemini, etc.) to help users write, optimise, and export ATS‑friendly resumes and cover letters. Built with Next.js 15, Supabase/PostgreSQL, and Stripe, it offers a free tier plus a $20 / month Pro plan for premium model access.

  • Project
    linkerlin/PUAX

    PUAX is a production‑ready runtime that adds a mind‑set layer to LLM agents. It provides arena/gate/dream primitives, thin‑prompt compression, a zero‑dependency Python SDK, hybrid trigger detection, 59 built‑in (and custom) roles, outcome‑driven verification, a Carbon Shield for human‑targeted manipulation detection, and a reproducible multi‑model benchmark suite. The system is accessed via an MCP server (`npx puax-mcp-server`) that injects native hooks into popular IDEs, and can be embedded directly into LangChain/AutoGen via a one‑line AMP middleware. MIT‑licensed and marked production‑ready.

  • Project
    microsoft/cognitive-services-speech-sdk-js

    A JavaScript SDK for integrating Microsoft Cognitive Services speech capabilities, enabling speech-to-text and text-to-speech functionality in browsers and Node.js.

  • Project
    SchroederNathan/clarity

    A speech-practice app for iOS and Android that provides live feedback and AI coaching to help users improve their articulation, pacing, and fluency.