# pluja/whishper

Transcribe any audio to text, translate and edit subtitles 100% locally with a web UI. Powered by whisper models!

Repository: https://github.com/pluja/whishper
Canonical: https://ross.abutalabs.com/products/whishper
Homepage: https://whishper-docs.pages.dev/
Language: Svelte
License: AGPL-3.0
License Family: copyleft
Topics: ai, audio-to-text, golang, subtitles, sveltekit, transcription, whisper, ui, webapp, speech-recognition, speech-to-text, stt, web, web-whisper
Last push: 2026-07-31T09:26:59+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 95, release rhythm 8, longevity 78
- inputs: {"age_days": 1103, "days_push": 33, "days_rel": 715, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3066, forks 178 (observed 2026-08-28T04:07:41.247747+00:00)

## What it is
Whishper is a self-hosted, 100% local audio transcription and subtitling suite with a web UI, powered by FasterWhisper. It transcribes audio/video (including from URLs via yt-dlp), translates transcriptions via LibreTranslate, and includes a subtitle editor with export to TXT, JSON, VTT, and SRT.

## Use cases
- transcribe audio files to text locally
- generate subtitles for videos
- translate transcriptions to another language
- edit srt subtitle files in a web ui
- transcribe youtube videos with whisper
- run speech-to-text offline without cloud services

## When to choose
- you need privacy-first, fully offline transcription
- you want an integrated subtitle editor and translation
- you want to transcribe media from URLs via yt-dlp
- you have an NVIDIA GPU or want fast CPU transcription

## When to avoid
- you need multi-user authentication (not yet supported)
- you want a maintained project - the main branch is frozen pending a v4 rewrite
- you need non-NVIDIA GPU acceleration
- you need a hosted or managed solution

## Facets
- artifact type: application
- maturity: maintenance
- function: speech-recognition, nlp, web-framework, self-hosted
- domain: speech-processing, self-hosted, artificial-intelligence
- platform: self-hosted
- tags: whisper, transcription, subtitles, faster-whisper, libretranslate, sveltekit, local-first, yt-dlp, audio, docker, web-server, linux, gpu

## Member repositories
- pluja/whishper (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:41.247747+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:28:12.023566+00:00, confidence not recorded.
  - readme: https://github.com/pluja/whishper (fetched 2026-08-28T04:07:41.247747+00:00, sha dddec6c5983c)
  - homepage: https://whishper-docs.pages.dev/ (fetched 2026-08-29T09:43:43.447110+00:00, sha b57e824b9098)
- Data as of 2026-08-30T08:39:29.467469+00:00.