# jianchang512/stt

Voice Recognition to Text Tool / 一个离线运行的本地音视频转字幕工具，输出json、srt字幕、纯文字格式

Repository: https://github.com/jianchang512/stt
Canonical: https://ross.abutalabs.com/products/stt
Homepage: https://pyvideotrans.com
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: speech, speech-recognition, speech-to-text, stt
Last push: 2026-01-22T08:38:53+00:00

## Health v2 (maintenance only)
Score: 45/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 63, release rhythm 9, longevity 69
- inputs: {"age_days": 979, "days_push": 223, "days_rel": 393, "gap_med": 315, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4766, forks 499 (observed 2026-08-28T04:08:59.191958+00:00)

## What it is
An offline local speech-to-text tool based on faster-whisper models that transcribes audio and video files into JSON, SRT subtitles, or plain text. It runs as a local web app with a browser UI and exposes an API compatible with OpenAI's audio transcription endpoint.

## Use cases
- generate srt subtitles from a video offline
- transcribe audio recordings to text locally
- self-host an openai whisper api replacement
- convert lecture recordings into transcripts
- batch transcribe media files with timestamps
- run speech recognition with cuda acceleration on nvidia gpu

## When to choose
- you need offline/private transcription without cloud APIs
- you want subtitle files (srt) with timestamps from audio/video
- you want an openai-compatible speech-to-text endpoint you self-host
- you have a local machine, optionally with an NVIDIA GPU

## When to avoid
- you need real-time streaming transcription
- you want a cloud-managed service with no local setup
- you need speaker diarization or advanced audio analysis
- you cannot install python/ffmpeg or download whisper models

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, audio-processing, video-processing, http-server, machine-learning
- domain: speech-processing, media, self-hosted
- platform: windows, python, cross-platform, self-hosted
- tags: faster-whisper, subtitles, srt, offline, transcription, openai-compatible-api, cuda, natural-language-processing, linux, macos

## Member repositories
- jianchang512/stt (main) score 45

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:59.191958+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 2026-08-29T18:18:50.492414+00:00, confidence not recorded.
  - readme: https://github.com/jianchang512/stt (fetched 2026-08-28T04:08:59.191958+00:00, sha 7f17217ed03f)
  - homepage: https://pyvideotrans.com (fetched 2026-08-29T09:02:14.429820+00:00, sha ea83000fc034)
- Data as of 2026-08-30T08:39:29.467469+00:00.