Multi-Agent Collaboration: Voice-overed video slide generator
Install Docker on your machine.
- Create a
.env
file in the root directory and add the following:
OPENAI_API_KEY=Your_OpenAI_API_Key
SERP_API_KEY=Your_Serp_API_Key
LANGCHAIN_API_KEY=Your_LangChain_API_Key
LANGCHAIN_TRACING_V2=true
LANGCHAIN_PROJECT="Multi-agent Collaboration"
- Run the docker run command to start the container
Update the .env
path if it is not in the root directory. (Instead of an environment file, you can also pass the environment variables directly to the docker run
command using the -e
flag.)
Update ${PWD}/projects
to the path where you want to create the projects if not current directory.
docker run --rm --env-file .env -it -v ${PWD}/projects:/app/projects cyrus2281/mac-slider-generator:latest
- Navigate to the root directory of the project and run the following command to build the Docker image
docker build -t mac-slider-generator .
- Create a
.env
file in the root directory and add the following:
OPENAI_API_KEY=Your_OpenAI_API_Key
SERP_API_KEY=Your_Serp_API_Key
LANGCHAIN_API_KEY=Your_LangChain_API_Key
LANGCHAIN_TRACING_V2=true
LANGCHAIN_PROJECT="Multi-agent Collaboration"
- Run the docker run command to start the container
docker run --rm --env-file .env -it -v ${PWD}:/app mac-slider-generator
Further environment variables can be added to the .env
file to customize the behavior of the app.
OPENAI_GPT_MODEL_NAME=Your_OpenAI_GPT_Model_Name
USE_OPENAI_FOR_TEXT_TO_AUDIO=Wether_to_use_OpenAI_for_text_to_audio
SLIDES_WATERMARK=Your_Slides_Watermark
EXTENDED_SLIDES=false
OPENAI_GPT_MODEL_NAME
: The OpenAI GPT model to use for generating text. Default isgpt-4o
.USE_OPENAI_FOR_TEXT_TO_AUDIO
: Whether to use OpenAI for text to audio conversion. Default istrue
.SLIDES_WATERMARK
: The watermark to add to the slides. Default isMAC-Slide-Generator by Cyrus Mobini
.EXTENDED_SLIDES
: Whether to generate more slides (1015 slides). Default is9 slides). This will increase the cost of the service.false
(around 6