Home › Models › MiniMax Music v3.0
MiniMax · Music v3.0 · Just Added

MiniMax Music v3.0 API

MiniMax's latest music generation model — turn lyrics and a style prompt into full songs (vocal or instrumental), exposed through NovAI's /v1/audio/speech endpoint and billed by real token usage.

$1.54 / 1M
Token rate
≈$0.154
Per song (ref)
URL
Output
$0
Platform fee
Sign Up - Get $2.00 Free Credit See All Pricing

Why use MiniMax Music v3.0 on NovAI?

  • Full-song generation - complete tracks from lyrics + style prompt
  • Vocal or instrumental - set is_instrumental for backing tracks
  • Latest v3.0 - MiniMax's newest music model
  • Style control - genre, mood and structure via the prompt field
  • Audio URL output - downloadable track link (valid ~24h)
  • Token billing - pay only for real upstream token usage

Best use cases

  • Original songs and demos
  • Background music for video
  • Jingles and ad audio
  • Game and app soundtracks
  • Instrumental backing tracks

Quick start

cURL — generate a song

curl https://aiapi-pro.com/v1/audio/speech \
  -H "Authorization: Bearer $NOVAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-music-v3.0",
    "prompt": "upbeat synthwave, driving bass, 80s retro",
    "lyrics": "[verse] Neon lights on the midnight road [chorus] We drive forever",
    "response_format": "url"
  }'

Music generation takes prompt (style) + lyrics; set is_instrumental: true for instrumental tracks. Returns a JSON body with audio_url (valid ~24h). Billed by real upstream token usage (usage.total_tokens × $1.54 / 1M) — a typical ~3-minute song is ~100k tokens ≈ $0.154.

Try MiniMax Music v3.0 today

Zero platform fee. Credits never expire. OpenAI-compatible API.

Sign Up Free