MiniMax Music 3

MiniMax-Music3 writes and sings a full song up to five minutes long from a style prompt and your lyrics, as a 44.1 kHz stereo WAV file.

MiniMax Music 3 (MiniMax-Music3) is MiniMax's open-weights music model, released in August 2026. It composes, arranges and sings a complete song up to five minutes long from a description of its style and the lyrics you give it. On the Artificial Analysis music arena it stood tenth of 14 models for vocal music in November 2026.

Describe the music in prompt: genre, mood, vocals, instruments and arrangement; for precise control write a structured caption with the genre, BPM, key, how the mood builds, the voice and a section-by-section arrangement. Write the words in lyrics, with a structure tag on a line of its own before each part: [intro], [verse], [pre-chorus], [chorus], [post-chorus], [bridge], [instrumental], [solo] or [outro]; words written on the same line after a tag are dropped. duration is the longest the song may be, 1 to 300 seconds (60 by default): the model may stop earlier. seed repeats a result.

Inputs: prompt and lyrics (both required), duration, seed, num_inference_steps (1-100, 30 by default: more steps improve the quality and take longer) and guidance_scale (0-20, 1.7 by default). Outputs: audio (the song, a 44.1 kHz 16-bit stereo WAV file, about 10 MB a minute), seed and duration (its real length in seconds). In our tests a 30-second song took about a minute and a quarter to make; a full-length song takes longer.

Price: billed on what the run uses, at list: $0.002 per second of music. The price shown before the run is held on your balance and is the longest the song can be (duration x $0.002: $0.12 for the default 60 seconds, $0.60 for five minutes); you are charged exactly what the run cost. It makes one song per request. It does not take a reference song or a melody, does not clone a voice and does not make speech or sound effects.

Price: $0.002 per second of duration. One run with default settings costs $0.12.

Run MiniMax Music 3 via API

curl -X POST https://api.flymy.ai/api/v1/flymyai/minimax-music-3/predict \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"Genre: lo-fi pop. BPM: 90. Soft piano, brushed drums, warm female voice.","lyrics":"[verse]\nMorning light on the window\nCoffee warm in my hands","duration":10}'

API documentation · Create a free account · Pricing

Related models