Sign up to save tools and stay up to date with the latest in AI
bg
bg
1

GitHub - neural-maze/melody_agents: Choose a topic, a music genre and wait for the agents to generate a song

Jun 15, 2024 - github.com
The article introduces a repository called Melody Agents, a crewAI application that generates songs based on a given topic and music genre. The application uses the Suno AI API and consists of three agents: the Web Researcher Agent, which searches the web for relevant information about the provided topic; the Lyrics Creator Agent, which generates high-quality lyrics from the research and adapts them to the given music genre; and the Song Generator Agent, which uses the Suno custom tool to interact with the Suno API and download two candidate songs.

To get started, users need to create a `.env` file and provide values for certain variables. The project uses docker-compose to create two containers, one for the Suno API logic and the other for the streamlit + crewAI logic. After building and starting the application, a Streamlit application is launched on the user's localhost, on port `8501`. The article includes images of what users should expect to see in their terminal and on the landing page.

Key takeaways:

  • The repository contains a crewAI application that generates songs based on a given topic and music genre using the Suno AI API.
  • The crew consists of three agents: Web Researcher Agent, Lyrics Creator Agent, and Song Generator Agent.
  • To use the application, you need to create a .env file and provide values for the variables SUNO_COOKIE, GROQ_API_KEY, and SERPER_API_KEY.
  • The application is configured using docker-compose, which creates two containers for the Suno API logic and the streamlit + crewAI logic.
View Full Article

Comments (0)

Be the first to comment!