← All models
MiniMax Music 3
music-3
Musicby minimax
MiniMax Music 3 is a high-performance music generation model for creating complete songs up to five minutes long
Details
- Accepts
- text
Pricing
- Price
- 0.156 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| seed | — | Random seed for reproducibility. If not provided, a random seed will be used. |
| lyricsrequired | string | The lyrics to sing. Structure tags such as [intro], [verse], [pre-chorus], [chorus], [post-chorus], [bridge], [instrumental], [solo] and [outro] must each be on their own line; text on the same line as a leading tag is dropped by the model's input contract. |
| promptrequired | string | Music description: style, mood, vocals, instrumentation and arrangement. For precise control use a Structured Caption with global metadata (genre, BPM, key, emotional progression), vocal details, and a section-by-section arrangement. |
| duration | number | Upper bound on the generated audio length in seconds. The model may stop earlier; the actual duration is returned in the output. |
| guidance_scale | number | Classifier-free guidance scale of the flow-matching stage. |
| num_inference_steps | integer | Number of flow-matching Euler steps per 8-second denoising chunk. More steps improve quality at the cost of speed. |
Output
| Field | Type | Description |
|---|---|---|
| seed | integer | The random seed used for the generation process. |
| audio | — | The generated audio file (44.1 kHz 16-bit stereo WAV). |
| duration | number | The actual duration of the generated audio in seconds (may be shorter than the requested duration). |