Scripttt is a Python web application that enables content creators to repurpose long-form video content into concise, engaging scripts for short-form platforms such as Instagram Reels and YouTube Shorts. Built with Gradio, Scripttt combines state-of-the-art transcription, speaker diarization, and script generation to deliver production-ready outputs that reflect the tone and style of the original conversation.
Features
Video File Uploads Only
Accepts direct uploads of video files (.mp4, .mkv, and other common formats). Audio-only files and external links are not supported.
Accurate Transcription
Utilizes OpenAI Whisper for high-quality speech-to-text conversion.
Speaker Diarization
Employs pyannote.audio to automatically identify and label speakers within the transcript.
Speaker-Tagged Transcript
Generates a clean, speaker-attributed transcript of the input video.
Short-Form Script Generation
Produces a concise, human-like script optimized for viral, short-form video content.
Privacy by Design
All processing occurs locally; no external URLs or remote media are accepted.
Installation
Clone the Repository
git clone https://github.com/your-username/scripttt.git
cd scripttt
Set Up a Virtual Environment (Recommended)
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
Install Dependencies
pip install -r requirements.txt
Configure Environment Variables
Create a .env file in the project root.
Add your Hugging Face and Google API credentials as environment variables.
Example:
