The BEST local AI music generator is here!
AI Search showed 6 AI tools in this video on . 4 are verified available in the EU. Each row below jumps to the exact second. Part of week 2026-33.
Tools shown in this video, with timestamps
Open-source text-to-music model with vocals and lyrics across genres and languages. Smallest quantized version is 2.5 GB. The creator installs it in ComfyUI and runs it locally; a 1-minute song took about 3-4 minutes on 16 GB VRAM. Quality is below the latest Suno models, and it is text-to-music only for now.
Live demoVideo generator available on Higgsfield. Generates up to 30 seconds in one pass with multiple shots and built-in audio. Supports up to 50 references and timestamp-based editing. Presented in the sponsor segment.
Popular platform for running open-source image, video and audio generators offline. Used here to run the Minimax text-to-music workflow from templates.
Live demoOpen-source music tool that can inpaint existing songs or generate music in the style of an existing song. Covered in a previous tutorial.
Open-source tool for generating individual music loops. It can use a loop as reference to generate additional tracks to stack into a full song, and can convert tracks to MIDI.
Open-source tool that transcribes a song into separate instrument tracks and MIDI notes, including vocals. The creator tried it in a Hugging Face Space and saw some errors. It comes in large (5.5 GB), medium and small (0.1B parameters, 412 MB) variants.
Live demo