realtime-transcriber-and-translator

The main functions of this software are as follows: It allows recording on a PC while performing real-time speech-to-text transcription and translation during the recording process. It also supports importing audio files. After the audio is imported, the software automatically starts processing without additional confirmation, and subsequent operations can only be performed after the processing is complete. The processed results are saved in multiple formats and stored in a project folder created in the user-specified location in chronological order. These include: Original audio Transcribed text Translated text Combined transcription + translation text Subtitle files (.SRT) Users can review and manage historical projects within the software or use any third-party media player for playback. The software includes a built-in playback feature. During playback, the corresponding transcript line is highlighted according to the current timestamp to indicate the progress. Users can click any line of the transcript to jump directly to the associated audio position. A keyword search function (Ctrl+F) is also provided to quickly locate the text within the transcription. Language and Interface Support This software supports a multilingual graphical user interface with 45 built-in interface languages. Users may also add new .ini files in the locales folder to further expand language support. Key Technical Features Equipped with Faster-Whisper-based offline transcription models, from lightweight and fast options to more accurate large models. Transcription models are stored in the models folder and can be added or removed based on hardware performance and user needs. Supports online translation and automatically switches to offline translation when no internet connection is detected. The argosmodels folder includes preloaded multilingual offline translation models, and users may add or delete model files as needed. Removing unused transcription and translation models can significantly reduce storage usage. Supports importing various mainstream audio formats without duration or file size limitations. Supports separate or synchronized display of transcription and translation text, with extended history and display management capabilities. Automatically adapts to light or dark mode based on system settings. This software is cost-effective and highly functional, addressing the scarcity and high cost of similar PC-based transcription software.