ScribeSE Logo

ScribeSE

AI-powered video transcription and analysis

Your data is stored locally in your browser

Select Video or Audio
How It Works
The Whisper model (~150MB) will download on first use and cache locally.
  1. Select your preferred transcription language (or auto-detect)
  2. Select a video or audio file (max 2GB)
  3. Audio is extracted and processed locally in your browser
  4. The Whisper AI model transcribes with timestamps
  5. Transcription is saved locally in your browser
  6. Generate AI summaries with chapters, key points, and FAQs
  7. Export summaries in Markdown, Plain Text, or JSON format
Transcription

Transcribe in English, Spanish, Japanese, and more

30+ Languages
AI Features

Auto-generated chapters, key points, and FAQs

Click the settings button to configure your preferred LLM provider (OpenAI, Ollama, or any OpenAI-compatible service).

Export

Download generated content as Markdown, Plain Text, or JSON

Interactive Playback

Navigate your video with clickable timestamps and verify content directly from the transcription