HiMeditator/auto-caption
A cross-platform real-time subtitle display software. 一个跨平台的实时字幕显示软件。
Supports multiple speech recognition engines (cloud-based Gummy/GLM-ASR and local Vosk/SOSV models) with pluggable architecture for custom engines, plus flexible translation via local Ollama, OpenAI-compatible APIs, or Google Translate. Built on a modular Python backend (packaged via PyInstaller) that decouples the subtitle engine from the Electron GUI, allowing CLI usage independently. Captures system audio or microphone input across Windows/macOS/Linux with customizable subtitle styling and export to SRT/JSON formats.
497 stars.
Stars
497
Forks
30
Language
TypeScript
License
MIT
Category
Last pushed
Feb 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/HiMeditator/auto-caption"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
XimilalaXiang/DeLive
DeLive is a cross-platform desktop app that captures system audio output and turns it into...
botbahlul/VOSK-Powered-Live-Subtitle-V3
ANDROID APP that can RECOGNIZE ANY LIVE AUDIO/VIDEO STREAMING (using free VOSK Speech...
botbahlul/pyvosklivesubtitle
PySimpleGUI based DESKTOP APP that can RECOGNIZE any live streaming in 23 languages that...
mmpneo/curses
Speech to Text and KB input captions for OBS, VRChat, Twitch chat and Discord
royshil/cloudvocal
Cloud AI live transcription and translation service plugin