Mureka AI Mureka V7.6 Generate Song API Documentation

Mureka AI Mureka V7.6 Generate Song API Documentation

Playground

Mureka AI V7.6 Generate Song is a fast AI music generation model that creates high-quality songs via the official Mureka API. Ready-to-use REST inference API for AI song generation, lyrics-to-music workflows, vocal music creation, demo production, creative audio projects, and professional music generation with simple integration, no coldstarts, and affordable pricing.

Features

Mureka AI V7.6 Recognize Song is a music recognition model for analyzing uploaded audio and identifying song-related information from the input track. It is suitable for song recognition, music metadata workflows, catalog matching, and other audio analysis tasks.

Why Choose This?

• Song recognition workflow Analyze an uploaded audio track and return recognized song information.

• Simple audio input Upload a single audio file and run recognition without additional configuration.

• Useful for metadata workflows Suitable for music identification, catalog management, and audio analysis pipelines.

• Fast API integration Easy to integrate into music tools, media workflows, and content analysis systems.

• Fixed pricing Uses a simple flat price per recognition request.

Parameters

How to Use

1. Upload your audio — provide the song or music clip you want to analyze.
2. Submit — run the recognition request.
3. Review the result — use the returned song recognition output in your workflow.

Example Use Case

Upload a music clip to identify the song and support catalog lookup or metadata verification workflows.

Pricing

Just $0.03 per request.

Best Use Cases

• Song identification — Recognize songs from uploaded audio clips.
• Music catalog workflows — Match tracks against library or metadata systems.
• Audio analysis pipelines — Use recognition as part of larger music-processing workflows.
• Content management — Verify or enrich music-related metadata.
• Media operations — Support ingestion, tagging, and review processes for music assets.

Pro Tips

• Upload clear audio for better recognition results.
• Use the cleanest source clip available when possible.
• Tracks with clear vocals and strong musical detail are generally easier to recognize.
• Avoid heavily distorted, noisy, or low-quality uploads when accuracy matters.

Notes

• audio is required.
• Pricing is fixed at $0.03 per request.
• If the uploaded song has unclear or indistinct lyrics, the model may be unable to extract lyric-related information accurately.
• Very noisy, low-quality, or heavily mixed audio may reduce recognition quality.

Related Models

• Mureka AI Stem Song — Process songs into stem-based outputs for remixing, editing, and production workflows.
• Mureka AI V8 Generate Song — Generate full songs from lyrics and optional reference inputs.
• Mureka AI V9 Generate BGM — Generate background music tracks from prompts.

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'
{
  "lyrics": "Waves rise softly under the morning light",
  "number_of_songs": 1,
  "output_format": "mp3"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/mureka-ai/mureka-v7.6/generate-song" \
  -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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 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) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters