MiniMax Music 1.5 creates complete, original songs up to 4 minutes long. This advanced AI model transforms your text prompts and optional reference audio into full musical pieces. It produces high-fidelity compositions featuring natural vocals, ethnic instruments, and live-style arrangements. The model supports custom lyrics and generates music across diverse genres and multicultural styles, making it ideal for use in soundtracks, video content, advertising, and professional music production.
vs Suno AI: MiniMax delivers more predictable and consistent full-length songs up to 4 minutes, with superior natural vocals guided by reference audio. Suno AI offers greater creative flexibility and dynamic style variation but with less predictable outcomes. MiniMax focuses on strong genre fidelity and vocal clarity, while Suno supports more experimental music generation styles.
vs Google Lyria 2: MiniMax excels in vocal expressiveness and ethnic instruments with clear song structure (Intro, Verse, Chorus, Bridge, Outro). Lyria 2 is praised for highly controllable, professional-grade instrumental music and nuanced creative controls like BPM and key signature. Lyria 2 targets producers needing deep customization primarily on instrumental music, while MiniMax offers end-to-end vocals and multi-genre coverage.
vs OpenAI Jukebox: MiniMax generates polished, studio-quality songs with focused vocal and instrumental clarity within 4 minutes, supporting user lyrics input. OpenAI Jukebox produces diverse stylistic music samples but struggles with long coherent song structure and natural vocal quality. MiniMax provides more refined and commercially usable audio, while Jukebox is better for creative explorations and genre experiments.
import requests, time headers = {"Authorization": "Bearer " + AIMLAPI_KEY} job = requests.post( "https://api.aimlapi.com/v2/generate/audio", headers=headers, json={ "model": "minimax/music-1.5", "prompt": "Upbeat lofi background music" }, ).json() gid = job["generation_id"] while True: res = requests.get(f"https://api.aimlapi.com/v2/generate/audio?generation_id={gid}", headers=headers).json() if res.get("status") in ("completed", "error", "failed"): break time.sleep(3) print(res)
const headers = { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }; const job = await (await fetch("https://api.aimlapi.com/v2/generate/audio", { method: "POST", headers, body: JSON.stringify({ "model": "minimax/music-1.5", "prompt": "Upbeat lofi background music" }), })).json(); let res; do { await new Promise((r) => setTimeout(r, 3000)); res = await (await fetch(`https://api.aimlapi.com/v2/generate/audio?generation_id=${job.generation_id}`, { headers })).json(); } while (!["completed", "error", "failed"].includes(res.status)); console.log(res);
# submit the job — the response contains "generation_id" curl -X POST https://api.aimlapi.com/v2/generate/audio \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"minimax/music-1.5","prompt":"Upbeat lofi background music"}' # then poll for the result until it is ready curl "https://api.aimlapi.com/v2/generate/audio?generation_id={generation_id}" -H "Authorization: Bearer $AIMLAPI_KEY"
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Output | |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
MiniMax Music 1.5 This page | Audio generation | |||
| Speech synthesis | ||||
| Speech synthesis | ||||
| Speech synthesis | ||||
| Speech synthesis |
MiniMax Music 1.5 takes audio, text as input and returns audio.
MiniMax Music 1.5 became available on December 5, 2025.
MiniMax Music 1.5 is priced at $0.039 / gen.
MiniMax Music 1.5 is billed per generation — a fixed charge per output rather than by prompt length.
MiniMax Music 1.5 was built by MiniMax.
Send a request to v2/generate/audio with minimax/music-1.5 as the model id.
Yes. MiniMax Music 1.5 is served through AI/ML API, so the same key and endpoint format used for other models applies.
