MiniMax Music 3 AI Music Generator

AI-generated music can sound like a complete song and still drift away from the original brief. Specified instruments may gradually disappear from the arrangement, the intended emotional character may weaken as the song develops, and a requested vocal style may appear in only one section instead of remaining coherent throughout the piece.

Music 3 introduces a more expressive music-description framework. Rather than summarizing an entire piece with a single global label, it uses Structured Captions to describe music at fine temporal granularity. These captions specify genre, tempo, time signature, key, use case, and production character, while also tracking emotional contour; the entry and exit of primary and supporting instruments; the development of groove and low-end energy; and section-level changes in vocal delivery, harmony, and vocal effects.

The challenge of long-form song generation is not merely generating for a longer duration; it is creating a credible progression across sections. Emotion must build and resolve, instruments must enter, layer, and recede at the right moments, and verses, choruses, bridges, and instrumental passages must all serve a unified direction.

Music 3 addresses this challenge at two levels. First, section tags in the lyrics - such as [intro], [verse], [pre-chorus], [chorus], [bridge], [instrumental], [solo], and [outro] - define the song's macrostructure. Second, the Structured Caption specifies the emotional development, instrumentation changes, vocal delivery, rhythmic foundation, ornamental timbres, and spatial effects at each stage, turning what changes, and where, into an explicit generation condition.

Compelling composition requires equally convincing sound. Music 3 delivers a substantial improvement in audio quality, producing mixes that are more open, clear, and balanced, with less congestion and muddiness.

Audio modeling begins with multi-layer residual vector quantization (RVQ). The first layer uses a 16,384-entry codebook dedicated to the music's core semantics and structure. Layers 2... each use a 1,024-entry codebook and progressively encode residual acoustic detail. During training, we first train the initial layer independently so that it captures core information as comprehensively as possible; all eight layers are then trained jointly. This hierarchical design balances semantic capacity, generation stability, and detail reconstruction while reducing error accumulation in long-sequence generation.

Vocals are often where the synthetic character of generated music is most apparent. High-frequency artifacts, rigid phrasing, unclear pronunciation, and unnatural breathing can break the listener's emotional connection even when the song is otherwise highly polished.

Music 3 introduces a new audio-rendering system designed to produce more natural, studio-quality vocal performances. The Structured Caption describes vocal timbre, delivery, techniques such as breathiness and falsetto, harmony arrangement, and effects such as delay and Auto-Tune in fine detail. Continuous hidden states fused from the global and local language models carry this performance information into the flow-matching and Flow-VAE generation process. Together, these mechanisms reduce the high-frequency digital artifacts common in generated vocals while improving control over melody, pronunciation, breathing, and layered harmonies.