5.9k Downloads
Overview
Command-line tool to generate high-quality SRT subtitles and burned-in captions from Hebrew or English video/audio, with optional Hebrew→English translation.
Key Advantages
1.Specialized Hebrew support using an ivrit.ai fine‑tuned model for strong transcription quality.
2.Uses OpenAI Whisper large-v3 for robust English (and likely auto-detected) transcription accuracy.
3.End-to-end workflow: transcription → SRT creation → optional translation → hardcoded or embedded subtitles in a single script.
4.Movie-style subtitle formatting (character limits, timing, line breaks) suitable for professional-looking results.
5.Fully local pipeline after model download (no constant external API calls implied), improving privacy and offline usability.
","Simple CLI interface with clear flags for common workflows (transcript,S
Use Cases
- Creating Hebrew/English subtitles for social media and messaging platforms (e.g., WhatsApp, Instagram, TikTok) where burned-in captions are required.
- Producing bilingual Hebrew→English captioned versions of lectures, sermons, webinars, and educational videos.
- Generating SRT files for YouTube, Vimeo, or LMS platforms from Hebrew or English source material.
- Batch-transcribing podcasts, interviews, or user research recordings in Hebrew/English into text and SRT.
- Producing accessible versions of marketing or product demo videos for Hebrew-speaking audiences, with optional English translation overlays.
Evaluation Scores
7.9
/ 10
Reliability
7.5
Functionality
8.5
Usability
7.5
Safety
8.5
Performance
7.0
Compatibility
7.5
Based on 1 evaluation · Latest: 3/19/2026
Download Trend
Loading...
Evaluation History (1)
7.9/103/19/2026▼
OS: linux-x64LLM: openai/gpt-5-nano
**Verdict:** A strong, focused CLI tool for generating professional subtitles from Hebrew/English video or audio, particularly valuable for Hebrew content creators and bilingual workflows. It shines for offline/batch processing and for producing hardcoded subtitles that display reliably on platforms like WhatsApp and social media.
**Strengths**
- High-quality transcription via ivrit.ai (Hebrew) and Whisper large-v3 (English).
- Supports automatic language detection, SRT generation, optional Hebrew→English translation, and both hardcoded and soft subtitles.
- Movie-style timing and line-breaking make the output usable with minimal manual cleanup.
**Risks / Limitations**
- Limited language coverage (primarily Hebrew and English; translation described only for Hebrew→English).
- Heavy models (~3GB each) and dependence on `ffmpeg-full` can mean slow processing and non-trivial setup, especially on low-end machines or constrained environments.
- CLI-only workflow; non-technical users or teams expecting a GUI/web interface may struggle.
- As with any ASR/MT system, outputs require human review for correctness, especially for technical, accented, or noisy audio.
**Best-suited scenarios**
- Developers or technical creators comfortable with the command line who need robust Hebrew and English subtitles.
- Content workflows where privacy/offline processing is preferred and local model downloads are acceptable.
- Preparing social media and messaging-friendly videos with burned-in, always-visible subtitles and/or Hebrew→English translated captions.
Comments (0)
No comments yet. Be the first!