Music Generation — MusicGen, Stable Audio, Suno, and the Licensing Earthquake
2026 music generation: Suno v5 and Udio v4 dominate commercial; MusicGen, Stable Audio Open, and ACE-Step lead open-source. The technical problem is mostly solved. The legal problem (Warner Music $500M settlement, UMG settlement) reshaped the field in 2025-2026. Text → a 30-second to 4-minute music clip, with lyrics, vocals, and structure. Three sub-problems: Instrumental generation. Text like "lo-fi hip-hop drums with warm keys" → audio. MusicGen, Stable Audio, AudioLDM. Song generation (with vocals + lyrics). "Country song about rainy Texas nights" → full song. Suno, Udio, YuE, ACE-Step. Conditional / controllable. Extend an existing clip, regenerate a bridge, swap genre, stem-separate, or inpaint. Udio's inpainting + stem separation is the 2026 feature to match. Music generation: token-LM vs diffusion, the 2026 model map Meta's MusicGen (2023, MIT) and many derivatives: condition on text/melody embeddings, autoregressively predict EnCodec tokens (32 kHz, 4 codebooks), decode with EnCodec. 300M - 3.3B params. Strong baseline; struggles past 30 seconds. ACE-Step (open-source, 4B XL released April 2026) extends this for full-song lyric-conditioned generation. The open community's closest thing to Suno. Stable Audio (2023) and Stable Audio Open (2024): latent diffusion on compressed audio. Excels at loops, sound design, ambient textures. Not great at structured full songs. AudioLDM / AudioLDM2: text-to-audio via T2I-style latent diffusion, generalized to music, sound effects, speech. Closed weights. Likely AR codec…
Music Generation — MusicGen, Stable Audio, Suno, and the Licensing Earthquake: 2026 music generation: Suno v5 and Udio v4 dominate commercial; MusicGen,…
This free lesson is part of the AI Engineering from Scratch curriculum. Read the full explanation, run the lesson code, and verify the result in the interactive reader or from the repository source.
Browse the complete course catalog or open this lesson on GitHub.