Mureka AI Mureka V9.5 Prompt To Song API Documentation

Mureka AI Mureka V9.5 Prompt To Song API Documentation

Playground

Mureka 9.5 Prompt-to-Song creates complete AI songs from text prompts via the Mureka official API, supporting prompt-based songwriting, vocals, instrumentals, music demos, social content, and creative audio production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Mureka V9.5 Prompt-to-Song generates one complete song from a natural-language prompt, optional style selections, and optional Mureka reference or vocal IDs. This endpoint can create both lyrics and musical arrangement for you, making it useful when you want a full song from a high-level creative direction.

Why Choose This?

• Prompt-to-song generation
  Generate a complete song from a written music description.

• Auto lyrics and arrangement
  Let the model create lyrics, melody, vocals, and arrangement from your prompt and style settings.

• Optional style control
  Use styles to guide the genre or musical direction.

• Reference ID support
  Use existing Mureka reference or vocal IDs for stronger style or vocal guidance.

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

Parameters

At least one useful generation control should normally be supplied, such as prompt, styles, reference_id, or vocal_id.

How to Use

1. Write a prompt optional — Describe the song theme, genre, mood, instruments, tempo, vocal style, and production direction.
2. Choose styles optional — Add one or more style selections to guide the genre or sound.
3. Add reference IDs optional — Use reference_id or vocal_id when you want stronger control.
4. Choose output format — Select mp3, wav, or flac.
5. Submit — Generate the full song and retrieve the output URL.

Pricing

Pricing is fixed at $0.750 per song.

Each request generates one song. output_format, styles, reference_id, and vocal_id do not add separate charges.

Best Use Cases

• Prompt-based song creation — Generate a full song from a short creative description.
• Auto lyrics workflows — Let the model create lyrics and arrangement automatically.
• Demo production — Quickly create song demos for creative review.
• Style exploration — Test different genres, moods, and vocal directions from the same idea.
• Vocal-guided generation — Use a vocal_id when a specific vocal identity or singing style matters.
• Reference-based music creation — Use reference_id to guide style, arrangement, or audio direction.

Pro Tips

• Use a clear prompt with genre, mood, tempo, instruments, vocal style, and theme.
• Add styles when you want stronger genre direction.
• Use reference_id when you want the song to follow an existing musical reference.
• Use vocal_id when vocal identity or singing style matters.
• Choose mp3 for compact delivery, or wav / flac when higher-quality audio files are needed.
• Keep the prompt focused on the final song direction instead of listing too many unrelated styles.

Notes

• reference_id can be prepared with Create Upload ID.
• vocal_id can be created with Vocal Clone.
• Use IDs from compatible Mureka workflows to avoid reference mismatch.
• Changing output_format does not add a format surcharge.

Related Models

• 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.
• Mureka V9.5 Prompt-to-Song — Generate a complete song from prompt and style guidance.

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'
{
  "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-v9.5/prompt-to-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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${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