AsrTools is a speech-to-text conversion tool with a graphical interface that transforms audio files into text-based subtitles without requiring GPU resources or complex configuration.
The tool solves the problem of converting audio to text by providing a user-friendly desktop application built with PyQt5 and qfluentwidgets. It uses multithreaded batch processing to handle multiple audio files concurrently and supports various ASR engines selectable through a dropdown menu. Users can drag and drop files or folders into the interface, initiate processing with a single button, and receive subtitle files in their original audio directory. The tool generates output in multiple formats including SRT, TXT, and ASS subtitle files. It also handles video files directly by automatically extracting audio before processing.
The tool suits users who need straightforward audio-to-text conversion without technical overhead, particularly those working with batch subtitle generation for video projects. It is distributed as a standalone executable for Windows that requires no environment setup, making it accessible to non-technical users. The project explicitly notes that more advanced functionality has been implemented in a related project focused on video captioning with LLM-based features.
Development activity shows ongoing refinement of both the core calling functionality and GUI features. The project maintains a public issue tracker for bug reports and feature requests. The README indicates that planned features including video file support, multiple output formats, one-click subtitle embedding, API integration, and a subtitle editor have been completed and moved to the related video captioning project, suggesting the maintainer has shifted focus to a more comprehensive tool while keeping this project available for simpler use cases.
