MiniMax Music v2.6 turns lyrics into complete songs with configurable style and structure, exposed through NovAI's /v1/audio/speech endpoint and billed by real token usage.
curl https://aiapi-pro.com/v1/audio/speech \
-H "Authorization: Bearer $NOVAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "minimax-music-v2.6",
"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.
Zero platform fee. Credits never expire. OpenAI-compatible API.
Sign Up Free