Mureka AI Vocal Clone API Documentation

Mureka AI Vocal Clone API Documentation

Playground

Mureka AI Vocal Clone is a fast AI voice cloning model that creates a Mureka vocal clone ID from a short vocal audio sample. Ready-to-use REST inference API for authorized vocal cloning, custom singing voices, AI song generation, music production, demo creation, personalized audio workflows, and professional voice-based music creation with simple integration, no coldstarts, and affordable pricing.

Features

Mureka AI Vocal Clone creates a reusable Mureka vocal clone ID from a short vocal audio sample. The returned vocal_id can then be used in compatible Mureka song-generation workflows to guide vocal identity and voice style.

Why Choose This?

• Voice cloning for Mureka workflows Create a reusable vocal identity from a single uploaded audio sample.

• Simple input Upload one vocal audio clip and generate a clone ID with minimal setup.

• Reusable output The result is a vocal_id that can be plugged into supported Mureka models later.

• Fast workflow Useful for personalized singing voices, recurring character vocals, and custom music-production pipelines.

• Production-ready API Suitable for music generation workflows that need a stable custom voice reference.

Parameters

How to Use

1. Upload your vocal sample — provide a clean audio clip of the voice you want to clone.
2. Submit — run the cloning request.
3. Save the returned ID — use the returned vocal_id in supported Mureka generation workflows.

Example Output

{ “id”: “140563370409985”, “vocal_id”: “140563370409985” }

Pricing

Just $5.00 per request.

Billing Rules

• Each vocal clone request costs $5.00
• Pricing is fixed per request

Best Use Cases

• Custom singing voice creation — Build a reusable voice identity for song generation.
• Recurring voice workflows — Keep a consistent vocal style across multiple songs.
• Music production prototyping — Test personalized vocal generation in downstream Mureka models.
• Character voice creation — Create a recognizable vocal identity for creative music projects.

Pro Tips

• Use a clean vocal recording with minimal background noise.
• Clear pronunciation and stable vocal tone usually improve clone quality.
• Save the returned vocal_id carefully so it can be reused later.
• Test the clone in downstream Mureka song workflows to validate the result.

Notes

• audio is required.
• The returned output is a Mureka-specific vocal_id.
• This ID is intended for use with Mureka-related models only.
• The result is not a general-purpose voice clone identifier outside the Mureka ecosystem.

Related Models

• Mureka AI V7.6 Generate Song — Generate songs from lyrics and optionally use a Mureka vocal ID.
• Mureka AI V8 Generate Song — Generate full songs with optional reference and vocal guidance.
• Mureka AI V9 Generate Song — Latest lyrics-to-song workflow in the Mureka lineup.
• Mureka AI O2 Generate Song — Higher-priced song generation workflow with the same reference-style interface.

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'
{
  "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/mureka-ai/vocal-clone" \
  -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