An AI-powered video processing toolkit for creating social media-optimized content with automated transcription, captioning, and thematic segmentation.
Desktop Application
Server Deployment
🚀 Check out our full project based on Clipify on https://github.com/adelelawady/Clipify-hub 🚀
Download and install the latest version:
# Via pip
pip install clipify
# From source
git clone https://github.com/adelelawady/Clipify.git
cd Clipify
pip install -r requirements.txt
from clipify.core.clipify import Clipify
# Initialize with basic configuration
clipify = Clipify(
provider_name="hyperbolic",
api_key="your-api-key",
model="deepseek-ai/DeepSeek-V3",
convert_to_mobile=True,
add_captions=True
)
# Process video
result = clipify.process_video("input.mp4")
# Handle results
if result:
print(f"Created {len(result['segments'])} segments")
for segment in result['segments']:
print(f"Segment {segment['segment_number']}: {segment['title']}")
clipify = Clipify(
# AI Configuration
provider_name="hyperbolic",
api_key="your-api-key",
model="deepseek-ai/DeepSeek-V3",
max_tokens=5048,
temperature=0.7,
# Video Processing
convert_to_mobile=True,
add_captions=True,
mobile_ratio="9:16",
# Caption Styling
caption_options={
"font": "Bangers-Regular.ttf",
"font_size": 60,
"font_color": "white",
"stroke_width": 2,
"stroke_color": "black",
"highlight_current_word": True,
"word_highlight_color": "red",
"shadow_strength": 0.8,
"shadow_blur": 0.08,
"line_count": 1,
"padding": 50,
"position": "bottom"
}
)
from clipify.audio.extractor import AudioExtractor
# Initialize audio extractor
extractor = AudioExtractor()
# Extract audio from video
audio_path = extractor.extract_audio(
video_path="input_video.mp4",
output_path="extracted_audio.wav"
)
if audio_path:
print(f"Audio successfully extracted to: {audio_path}")
from clipify.audio.speech import SpeechToText
# Initialize speech to text converter
converter = SpeechToText(model_size="base") # Options: tiny, base, small, medium, large
# Convert audio to text with timing
result = converter.convert_to_text("audio_file.wav")
if result:
print("Transcript:", result['text'])
print("\nWord Timings:")
for word in result['word_timings'][:5]: # Show first 5 words
print(f"Word: {word['text']}")
print(f"Time: {word['start']:.2f}s - {word['end']:.2f}s")
from clipify.video.converter import VideoConverter
# Initialize video converter
converter = VideoConverter()
# Convert video to mobile format with blurred background
result = converter.convert_to_mobile(
input_video="landscape_video.mp4",
output_video="mobile_video.mp4",
target_ratio="9:16" # Options: "1:1", "4:5", "9:16"
)
if result:
print("Video successfully converted to mobile format")
from clipify.video.converterStretch import VideoConverterStretch
# Initialize stretch converter
stretch_converter = VideoConverterStretch()
# Convert video using stretch method
result = stretch_converter.convert_to_mobile(
input_video="landscape.mp4",
output_video="stretched.mp4",
target_ratio="4:5" # Options: "1:1", "4:5", "9:16"
)
if result:
print("Video successfully converted using stretch method")
from clipify.video.processor import VideoProcessor
# Initialize video processor with caption styling
processor = VideoProcessor(
# Font settings
font="Bangers-Regular.ttf",
font_size=60,
font_color="white",
# Text effects
stroke_width=2,
stroke_color="black",
shadow_strength=0.8,
shadow_blur=0.08,
# Caption behavior
highlight_current_word=True,
word_highlight_color="red",
line_count=1,
padding=50,
position="bottom" # Options: "bottom", "top", "center"
)
# Process video with captions
result = processor.process_video(
input_video="input_video.mp4",
output_video="captioned_output.mp4",
use_local_whisper="auto" # Options: "auto", True, False
)
if result:
print("Video successfully processed with captions")
# Process multiple video segments
segment_files = ["segment1.mp4", "segment2.mp4", "segment3.mp4"]
processed_segments = processor.process_video_segments(
segment_files=segment_files,
output_dir="processed_segments"
)
The VideoProcessor provides powerful captioning capabilities:
from clipify.video.cutter import VideoCutter
# Initialize video cutter
cutter = VideoCutter()
# Cut a specific segment
result = cutter.cut_video(
input_video="full_video.mp4",
output_video="segment.mp4",
start_time=30.5, # Start at 30.5 seconds
end_time=45.2 # End at 45.2 seconds
)
if result:
print("Video segment successfully cut")
from clipify.core.text_processor import SmartTextProcessor
from clipify.core.ai_providers import HyperbolicAI
# Initialize AI provider and text processor
ai_provider = HyperbolicAI(api_key="your_api_key")
processor = SmartTextProcessor(ai_provider)
# Process text content
text = "Your long text content here..."
segments = processor.segment_by_theme(text)
if segments:
for segment in segments['segments']:
print(f"\nTitle: {segment['title']}")
print(f"Keywords: {', '.join(segment['keywords'])}")
print(f"Content length: {len(segment['content'])} chars")
clipify/
├── clipify/
│ ├── __init__.py # Package initialization and version
│ ├── core/
│ │ ├── __init__.py
│ │ ├── clipify.py # Main Clipify class
│ │ ├── processor.py # Content processing logic
│ │ ├── text_processor.py # Text analysis and segmentation
│ │ └── ai_providers.py # AI provider implementations
│ ├── video/
│ │ ├── __init__.py
│ │ ├── cutter.py # Video cutting functionality
│ │ ├── converter.py # Mobile format conversion
│ │ ├── converterStretch.py # Alternative conversion method
│ │ └── processor.py # Video processing and captions
│ ├── audio/
│ │ ├── __init__.py
│ │ ├── extractor.py # Audio extraction from video
│ │ └── speech.py # Speech-to-text conversion
│ └── utils/ # Utility functions
│ ├── __init__.py
│ └── helpers.py
├── .gitignore # Git ignore rules
├── LICENSE # MIT License
├── MANIFEST.in # Package manifest
├── README.md # Project documentation
├── requirements.txt # Dependencies
└── setup.py # Package setup
hyperbolic: Default provider with DeepSeek-V3 modelopenai: OpenAI GPT models supportanthropic: Anthropic Claude modelsollama: Local model deployment1:1, 4:5, 9:16We welcome contributions! Here's how you can help:
git checkout -b feature/amazing-feature)git commit -m 'Add amazing feature')git push origin feature/amazing-feature)Please read our Contributing Guidelines for details.
This project is licensed under the MIT License - see the LICENSE file for details.
FAQs
A powerful tool for processing video content into social media-friendly segments
We found that clipify demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Security News
Socket and Seal Security collaborate to fix a critical npm overrides bug, resolving a three-year security issue in the JavaScript ecosystem's most popular package manager.
Security News
TypeScript is porting its compiler to Go, delivering 10x faster builds, lower memory usage, and improved editor performance for a smoother developer experience.
Research
Security News
The Socket Research Team has discovered six new malicious npm packages linked to North Korea’s Lazarus Group, designed to steal credentials and deploy backdoors.