MiniMax Music 3.0
MiniMax Music 3.0 is a music generation model from MiniMax that creates songs from lyrics or as instrumentals at $0.15 per song.
MiniMax
WaveSpeedText-to-music generation with vocal and instrumental modes
MiniMax Music 3.0 is a music generation model developed by MiniMax and made available through the Wavespeed provider. It accepts lyric prompts as text input and produces full songs, with options to toggle between vocal and instrumental output, and controls for bitrate and sample rate. The model is tagged as supporting source audio, indicating it works with audio-level generation rather than symbolic or MIDI-based output.
MiniMax Music 3.0 is suited for developers and creators who need programmatic music generation with configurable audio quality settings. It operates on a per-song pricing model at $0.15 per song and carries a context window of 2000 tokens for lyric input. The model is listed as the latest release in the MiniMax music generation line and is available for use directly through MindStudio without requiring separate API key setup.
What MiniMax Music 3.0 supports
Lyric-Based Generation
Generates songs from text lyric prompts supplied as a standard prompt input, with a context window of up to 2000 tokens for lyric content.
Instrumental Toggle
Allows switching between vocal and fully instrumental output via a toggle group input, giving control over whether vocals are included in the generated track.
Bitrate Control
Exposes a selectable bitrate setting so users can configure the audio compression quality of the generated song output.
Sample Rate Selection
Provides a selectable sample rate option, letting users specify the audio fidelity and frequency resolution of the generated file.
Source Audio Output
Produces output as source audio rather than symbolic notation or MIDI, delivering a rendered audio file directly from the generation pipeline.
Ready to build with MiniMax Music 3.0?
Get Started FreeCommon questions about MiniMax Music 3.0
How much does MiniMax Music 3.0 cost to use?
MiniMax Music 3.0 is priced at $0.15 per song generated, regardless of whether the output is vocal or instrumental.
What is the context window for lyric input?
The model supports a context window of 2000 tokens, which applies to the lyric prompt input used to guide song generation.
Can I generate instrumental tracks without vocals?
Yes. The model includes an instrumental toggle input that lets you switch between vocal and instrumental-only output before generating a song.
What audio quality settings are available?
The model exposes two configurable settings: bitrate and sample rate. Both are selectable inputs, allowing you to adjust the compression and frequency resolution of the generated audio file.
What is the release date of MiniMax Music 3.0?
MiniMax Music 3.0 has a listed release date of August 2026 and is tagged as the latest version in the MiniMax music generation lineup.
Parameters & options
Song lyrics with optional structure tags such as [Verse], [Chorus], and [Bridge]. Leave empty to auto-generate lyrics from the prompt. You can use a newline to separate each line, two newlines for a pause, and ## around lyrics to add accompaniment. Valid input: 10-3000 characters when provided.
Generate a backing track without vocals.
Audio bitrate in bits per second. Higher values produce better audio quality.
Audio sample rate in Hz. Higher values capture more detail.
Explore similar models
MiniMaxMiniMax Music 2.5
MiniMax Music 2.5 is a music generation model that converts lyrics into songs with configurable bitrate and sample rate.
MiniMaxMiniMax M3
MiniMax M3 is a multimodal text generation model from MiniMax with a 524,288-token context window.
MiniMaxMiniMax H3
MiniMax H3 is a video generation model from MiniMax that supports text-to-video, image-to-video, and reference-based video creation at up to 2K resolution.
GoogleLyria 3
Lyria 3 is a music generation model from Google that produces audio from text prompts with a 5000 token context window.
ElevenLabsElevenLabs Music
ElevenLabs Music is a music generation model that produces audio tracks from text prompts with a 2000 token context window.
ByteDanceSeedance 2.5 Turbo
Seedance 2.5 Turbo is a video generation model from ByteDance that supports text-to-video, image-to-video, and video editing modes.
Start building with MiniMax Music 3.0
No API keys required. Create AI-powered workflows with MiniMax Music 3.0 in minutes — free.