At Video SDK, we’re building tools to help companies create world-class collaborative products with capabilities of live audio/videos, compose cloud recordings/RTMP/HLS, and interaction APIs.
For more detailed information, visit the Video SDK Documentation.
The repository is organized as follows:
-
capture-image: Contains scripts for capturing images.
-
face-detection-and-landmarks: Includes scripts for face detection and landmark identification.
-
face-recognition: face recognition feature on participant stream. coming soon
-
python-rtc: Basic Python RTC to join VideoSDK Meeting.
-
transform-audio: audio transformation. coming soon
-
transform-video: Contains scripts for video transformation.
-
vision-ai: Contains vision AI related scripts.
To get started with the Video SDK Face Detection, follow these steps:
-
Clone the repository:
git clone https://github.com/videosdk-live/videosdk-rtc-python-sdk-example.git
-
Change Directory:
Let's run a example that detects the face from the stream. change the directory to
face-detection-and-landmarks
.cd videosdk-rtc-python-sdk-example/face-detection-and-landmarks
-
Install dependencies:
pip install -r requirements.txt
-
Set up environment variables:
- Copy the example environment file:
cp .env.example .env
- Update
.env
with your credentials and configurations.
- Run a sample script:
- For example, to run the face detection script:
python face_detection.py