

SRTWhisper
Transcribes video speech into subtitles using advanced AI models with multilingual translation, live subtitle editing and preview, robust quality checks, support for offline processing, customizable exports as SRT, ASS, or burnt-in, suitable for creators and professionals.
Cost / License
- Pay once
- Proprietary
Platforms
- Mac
SRTWhisper News & Activities
Recent activities
- Danilo_Venom updated SRTWhisper
- zhiii0x added SRTWhisper
- zhiii0x added SRTWhisper as alternative to Handy STT, Vibe Transcribe, Voxtral and OpenWhispr
SRTWhisper information
What is SRTWhisper?
SRTWhisper is a software solution for creating multilingual subtitles for videos. It uses Whisper AI speech recognition and LLM-powered translation for transcribing, translating, editing, exporting, and burning-in subtitles.
Key features include Speech Transcription, Multiple Translation Engines, a Subtitle Editor with Live Preview, a Quality Checker, and Flexible Export options. For transcription, it uses WhisperKit with seven model sizes for speed and accuracy balance, automatic language detection, and manual source language selection. The translation engines include local LLM, OpenAI GPT models, Ollama local server, and a custom OpenAI-compatible API endpoint.
The Subtitle Editor allows users to edit text and timing, add, delete, merge, or split segments, and adjust start/end times. The Quality Checker identifies common issues like overlapping timestamps, high reading speed, and long lines and offers one-tap fixes. Users can export as SRT, WebVTT, or ASS/SSA, or burn subtitles into the video with customizable font, size, color, outline, and position.
SRTWhisper is suitable for video creators needing multilingual subtitles, professionals transcribing interviews, lectures, or meetings, and anyone preferring local processing over cloud data storage.


