Freedom251 › AI Video Caption Generators
Whishper Reloaded

What Whishper Reloaded is
Whishper Reloaded is a free, open-source transcription and subtitle workspace that you self-host. Its web interface accepts uploaded audio or video, URLs supported by yt-dlp, and media formats readable by FFmpeg. Faster-Whisper handles transcription on a CPU or with NVIDIA GPU acceleration through CUDA, and the README says it supports more than 99 languages. Results can be downloaded as TXT, JSON, VTT, or SRT, or copied as raw text. A subtitle editor highlights media position, warns about characters-per-second rates, supports splitting and inserting segments, and lets users choose a subtitle language. LibreTranslate handles translation into languages that service supports. Transcription, translation, and editing run locally, with offline operation possible after Docker images and the Whisper model are downloaded. Docker Compose can run backend, frontend, and transcription API containers together or across machines. The documented stack includes MongoDB and Nginx.
Who it suits
It suits people who want local, self-hosted transcription, translation, and subtitle editing through a browser. It is also relevant to users needing CPU processing, NVIDIA acceleration, Docker deployment, or offline work.
What it does well
- Free to self-host
- Local processing and offline capability
- CPU and NVIDIA GPU modes
- Exports TXT, JSON, VTT, and SRT
- Supports more than 99 languages
What to know first
- Requires self-hosting on your hardware
- Offline use requires downloaded images and model
- Translation depends on LibreTranslate languages
- Licensed under AGPL-3.0
Plans
| Plan | Billed and limits | Price |
|---|---|---|
| Free self-hosted | Free to self-host on your own hardware · open-source under AGPL-3.0 | Free |
As github.com lists them, read 12 Oct 2026. The maker's own page has the final word.
Verdict
Whishper Reloaded brings transcription, translation, and subtitle editing into a self-hosted web interface. Its Docker-based deployment and local-processing model suit technically minded users managing their own hardware.
Facts from Whishper Reloaded's own pages
- Architecture
- The backend, frontend, and transcription API can run as separate containers and can be split across machines. · github.com, 12 Oct 2026
- Components
- The documented stack includes Faster-Whisper, LibreTranslate, MongoDB, and Nginx. · github.com, 12 Oct 2026
- Deployment
- The project provides a Docker Compose setup and allows components to run on one machine or across multiple machines. · github.com, 12 Oct 2026
- Exports
- Transcriptions can be downloaded as TXT, JSON, VTT, or SRT, or copied as raw text. · github.com, 12 Oct 2026
- Formats and URLs
- It supports media formats readable by FFmpeg and URLs supported by yt-dlp. · github.com, 12 Oct 2026
- Free plan
- Yes · github.com, 19 Sept 2026
- Hardware
- It supports CPU transcription and NVIDIA GPU acceleration via CUDA. · github.com, 12 Oct 2026
- Inputs
- Users can upload media or transcribe URLs supported by yt-dlp; it also supports formats FFmpeg can read. · github.com, 12 Oct 2026
- Language support
- The README says Faster-Whisper supports more than 99 languages, including Italian, French, German, Spanish, and Japanese. · github.com, 12 Oct 2026
- License and cost
- The README says it is open source under AGPL-3.0 and free to self-host on your own hardware. · github.com, 12 Oct 2026
- Local operation
- Transcription, translation, and subtitle editing run locally, and the project says it can work offline after Docker images and the Whisper model are downloaded. · github.com, 12 Oct 2026
- Local processing
- The project says transcription, translation, and subtitle editing run locally and can work offline. · github.com, 12 Oct 2026
- Maintenance
- The README says devdema maintains Whishper Reloaded solo and credits Pluja as the original Whishper creator and a main contributor to the original codebase. · github.com, 12 Oct 2026
- Maintenance and contributions
- The README says DevDema maintains the fork and welcomes contributions through pull requests. · github.com, 12 Oct 2026
- Notable features
- Whishper Reloaded adds transcription search, pagination, renaming, JSON import/export, audio-only editing, and playback and segment navigation shortcuts. · github.com, 12 Oct 2026
- Other components
- The documented stack includes MongoDB for transcription information and Nginx as a proxy. · github.com, 12 Oct 2026
- Pricing and license
- The README describes the software as free to self-host on your own hardware and identifies the repository license as AGPL-3.0. · github.com, 12 Oct 2026
- Purpose
- Whishper Reloaded is a self-hosted audio transcription suite with a web UI for transcribing, translating, and editing subtitles. · github.com, 12 Oct 2026
- Subtitle editing
- The editor includes media-position highlighting, characters-per-second warnings, segment splitting and insertion, and subtitle language selection. · github.com, 12 Oct 2026
- Subtitle editor
- The editor includes media-position highlighting, characters-per-second warnings, segment splitting and insertion, and subtitle language selection. · github.com, 12 Oct 2026
- Subtitle export
- other formats · github.com, 19 Sept 2026
- Transcription
- It transcribes audio and video files or URLs supported by yt-dlp. · github.com, 12 Oct 2026
- Transcription engine
- It uses Faster-Whisper as its Whisper backend and supports CPU and NVIDIA GPU modes. · github.com, 12 Oct 2026
- Translation
- It translates transcriptions using LibreTranslate into languages that service supports. · github.com, 12 Oct 2026
Where Whishper Reloaded stands on Freedom251
- AI Video Caption Generators#52 of 99