Mureka AI Mureka V9.5 Generate Bgm API Documentation

Mureka AI Mureka V9.5 Generate Bgm API Documentation

Playground

Mureka 9.5 Generate BGM creates background music from prompts, supporting instrumental tracks, mood-based scoring, video BGM, game audio, ads, social content, and creative production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Mureka V9.5 Generate BGM creates one instrumental background-music track from a text prompt. Describe the mood, genre, instruments, tempo, and scene context, then choose an output format to generate music for videos, games, ads, social content, and other creative workflows.

Why Choose This?

• Prompt-to-BGM generation
  Generate instrumental background music directly from a text prompt.

• Instrumental output
  Create background tracks without requiring lyrics or vocal references.

• Flexible style control
  Describe genre, mood, tempo, instruments, arrangement, and production direction.

• Multiple output formats
  Choose mp3, wav, or flac based on your delivery needs.

• Simple music workflow
  Provide a prompt, select an output format, and generate one complete BGM track.

Parameters

How to Use

1. Write your prompt — Describe the background music style, mood, tempo, instruments, and intended scene.
2. Choose output format — Select mp3, wav, or flac.
3. Submit — Generate the BGM track and retrieve the output URL.

Pricing

Pricing is fixed at $0.225 per BGM track.

Each request generates one track. Changing output_format does not add a format surcharge.

Best Use Cases

• Background music generation — Create instrumental tracks for video, games, podcasts, or creative projects.
• Video and social content — Generate music beds for shorts, reels, ads, and promotional clips.
• Game and app audio — Create loop-friendly or scene-matching background music.
• Commercial and brand content — Produce mood-specific music for campaigns and product videos.
• Creative prototyping — Test different genres, tempos, and emotional directions quickly.

Pro Tips

• Describe the intended scene or use case, such as cinematic trailer, cozy vlog, product ad, fantasy game menu, or relaxing background loop.
• Include genre, mood, tempo, instruments, and production style for better control.
• Use words like ambient, cinematic, lo-fi, orchestral, electronic, or acoustic when style matters.
• Choose mp3 for compact delivery, or wav / flac when higher-quality audio files are needed.
• Keep the prompt focused on instrumental background music rather than lyrics or vocals.

Notes

• Use prompt to control the background music direction.
• Changing output_format does not add a format surcharge.

Related Models

• Mureka V9.5 Prompt-to-Song — Generate a song from a music prompt.
• Mureka V9.5 Generate Song — Generate a complete song from supplied lyrics.
• Mureka V9.5 Generate BGM — Generate instrumental background music from a text prompt.

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",
  "output_format": "mp3"
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/mureka-ai/mureka-v9.5/generate-bgm" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

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

Parameters

Task Submission Parameters

Request Parameters

Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.

Response Parameters

Result Request Parameters

Result Response Parameters