@Honcia13: Highly recommend an open-source speech-to-subtitle tool! Incredible speed and top-notch quality! Supports multiple languages including Chinese, Japanese, Korean, English, etc., with specially optimized formatting rules for natural and professional subtitles. It's a desktop tool based on PySide6 + ElevenLabs API that can convert audio/video files or JSON…

Strongly recommend an open-source speech-to-subtitle tool! Extremely fast with top-notch quality! Supports multiple languages including Chinese, Japanese, Korean, English, and more, with specially optimized formatting rules for natural and professional subtitles. This is a desktop tool based on PySide6 + ElevenLabs API that intelligently converts audio/video files or JSON transcripts into high-quality SRT subtitles, especially suited for CJK and English formatting conventions. Perfect for video creators, editors, course makers, and subtitle producers! https://github.com/cylind/scribe2srt… — # cylind/scribe2srt Source: https://github.com/cylind/scribe2srt # Scribe2SRT Scribe2SRT is a professional audio/video to subtitle tool. By integrating ElevenLabs speech recognition technology and intelligent subtitle segmentation algorithms, subtitle production becomes simple and efficient. ## 🚀 Key Features - 🎯 High-quality transcription: Based on ElevenLabs’ advanced speech recognition technology - 🌍 Multi-language support: Supports Chinese, English, Japanese, Korean, and more - 📝 Professional subtitle standards: Follows industry standards like Netflix for subtitle production - ⚡ Smart segmentation algorithm: Semantic segmentation based on punctuation priority, maintaining sentence integrity - 🔄 Smart retry mechanism: Automatically saves temporary files on failure, quick recovery on retry - 🎨 User-friendly interface: Clean and intuitive graphical user interface with drag-and-drop support - 📊 Real-time progress feedback: Clear progress display and status prompts ## 💻 Installation & Usage ### Quick Start 1. Go to the Releases page (https://github.com/cylind/scribe2srt/releases) and download the latest version 2. Extract and run the program directly 3. It is recommended to install FFmpeg: For video file processing, improving compatibility and efficiency Run from source (click to expand) #### Installation Steps 1. Download the project bash git clone https://github.com/your-username/scribe2srt.git cd scribe2srt 2. Install dependencies bash pip install -r requirements.txt 3. Run the program bash python app.py ## 📖 Usage Instructions ### Basic Workflow 1. Select input file - Click the “Select File” button or drag and drop a file into the program window - Supports three input types: - Audio files: All common audio formats (MP3, WAV, FLAC, M4A, AAC, OGG, etc.) - Video files: All common video formats (MP4, MOV, MKV, AVI, FLV, WEBM, etc.) - JSON transcript files: ElevenLabs format transcription data 2. Configure processing options - Language selection: Select the source language or use “Auto Detect” - Audio event marking: Choose whether to mark non-speech events (e.g., laughter, applause) 3. Start processing - Click the “Generate Subtitles” button to begin transcription - The program will display detailed processing progress 4. Get results - After processing, the SRT subtitle file is automatically saved in the same directory as the source file - The program shows the output file path ### Subtitle Quality Standards This tool follows professional subtitle production standards: - Duration control: Minimum 0.83 seconds, maximum 7.0 seconds - Character density: CJK languages up to 11 characters per second, Latin languages up to 15 characters per second - Line length limit: CJK languages max 25 characters per line, Latin languages max 42 characters per line - Semantic integrity: Prioritizes maintaining sentence completeness, segmentation based on punctuation priority ## ⚙️ Advanced Settings ### Subtitle Parameter Adjustment Via the “Subtitle Settings” menu, you can adjust: - Subtitle display duration and gap - Character density limits - Characters per line limit ### Large File Processing - Automatic segmentation for long files (90+ minutes) - Supports concurrent processing for faster speed - Smart retry mechanism ensures processing success ## 🔧 Technical Highlights ### Smart Segmentation Algorithm - Two-stage processing: Sentence pre-segmentation + intelligent merging - Punctuation priority: Segmentation strategy based on linguistic rules - Semantic integrity: Avoids breaking sentence structure - Multi-language optimization: Differentiated processing for different languages ## 📄 License This project is licensed under the MIT license. — If this project helps you, please give us a ⭐ Star!