stt and realtime-stt
These are ecosystem siblings where the second is a simplified, real-time variant of the first—both offline STT tools from the same author targeting the same use case but with different architectural approaches (batch processing with multiple output formats vs. streaming inference).
About stt
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
This tool helps you convert spoken words from audio or video files into written text. You simply upload your media, choose the language and desired output format (like plain text, SRT subtitles with timestamps, or JSON), and it generates the transcript. This is perfect for content creators, transcribers, or anyone needing to quickly document spoken content from media without relying on online services.
About realtime-stt
jianchang512/realtime-stt
一个极简的本地离线实时语音转文字工具
This tool helps you convert spoken Chinese (or mixed Chinese-English) into punctuated text in real-time, making it easier to capture important information. It takes audio input from your microphone and outputs text directly into a desktop application. This is ideal for professionals like students, journalists, meeting facilitators, or anyone who needs to quickly transcribe spoken words.
Scores updated daily from GitHub, PyPI, and npm data. How scores work