Minimax Music Cover API Documentation

Minimax Music Cover API Documentation

Playground

MiniMax Music Cover transforms existing songs into completely different styles — new arrangement, new vocal character, same melody. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Features

MiniMax Music Cover transforms any audio track into a new musical style. Upload a song and describe the target sound — genre, instruments, tempo, mood — and the model generates a reimagined cover version that captures your vision while preserving the core structure of the original.

Why Choose This?

• Style transfer for music Reimagine any track in a completely different genre or era — turn a pop song into a jazz arrangement, or a ballad into an 80s synth-pop anthem.

• Detailed style control Describe the exact sonic character you want — instruments, BPM, vocal style, production techniques, and mood — for precise results.

• Works on any audio Upload songs, instrumentals, demos, or recordings in any style as the source material.

• Prompt Enhancer Built-in tool to automatically improve your music style descriptions for richer output.

Parameters

How to Use

1. Write your prompt — describe the target genre, instruments, BPM, vocal style, and production feel. Use the Prompt Enhancer for richer results.
2. Upload your audio — provide the source track via URL, file upload, or microphone recording.
3. Submit — generate and download your reimagined cover.

Example Prompt

Upbeat City Pop 80s retro: funky bassline, bright synth chords, groovy drum machine, clean female vocal, romantic saxophone solo, 110 BPM

Pricing

Just $0.15 per cover.

Best Use Cases

• Music production — Rapidly prototype new genre arrangements or production styles from existing demos.
• Creative exploration — Discover how a track sounds in a completely different musical era or style.
• Content creation — Generate unique background music covers for videos, podcasts, and social media.
• Remix & reinterpretation — Create style-shifted versions of your own recordings for different audiences.
• Inspiration & ideation — Use covers as creative jumping-off points for new compositions.

Pro Tips

• Be specific in your prompt — include genre, BPM, key instruments, vocal style, and production cues like “clean mix” or “analog warmth.”
• The more distinct your target style is from the source audio, the more dramatic and interesting the transformation.
• Use the Prompt Enhancer to expand a simple style reference into a detailed, production-ready description.
• Try the same source audio with different prompts to explore multiple style directions quickly.

Notes

• Both prompt and audio are required fields.
• Ensure audio URLs are publicly accessible if using a link rather than a direct upload.
• Please ensure your content complies with MiniMax’s usage policies.

Related Models

• MiniMax Music 2.6 — Generate complete original songs from lyrics and a style prompt.
• MiniMax Music 2.5 — Previous generation MiniMax music generation model.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/minimax/music-cover" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters