This fork introduces a Radio Station feature where AI generates continuous radio music. The process involves two key components:
LLM: Generates the lyrics for the songs. ACE: Composes the music for the generated lyrics.
Due to the limitations of slower PCs, the demo video includes noticeable gaps (approximately 4 minutes) between the generated songs.
If your computer struggles to stream songs continuously, increasing the buffer size will result in a longer initial delay but fewer gaps between songs (until the buffer is depleted again).
By default the app attempts to load the model file gemma-3-12b-it-abliterated.q4_k_m.gguf from the same directory. However, you can also use alternative LLMs. Note that the quality of generated lyrics will vary depending on the LLM’s capabilities.
Nice idea. I recenty hacked together an AI radio station that mimics two radio hosts and queues music from Spotify. Somewhat similar to the Podcast scripts ( document-to-podcast, podcast-llm, podcastify, notebooklm ) just with the instructions to make up dialogue for a radio show and pick songs. Seems to work very well. Now I need it to generate 2h mp3 files and somehow connect that to Icecast, in order to stream it.
Also nice to see gemma-3-12b can do rhymes. I’ve always had issues with that and resorted to ChatGPT to write song lyrics, since the small local models couldn’t really do it properly. Is gemma3 a good pick for this? Any other local models I might want to try for song lyrics?