Mureka AI Extend Lyrics API Documentation

Mureka AI Extend Lyrics API Documentation

Playground

Try it on WaveSpeedAI!

Mureka AI Extend Lyrics is a fast AI lyrics generation model that extends existing song lyrics via the official Mureka API. Ready-to-use REST inference API for continuing lyric ideas, songwriting workflows, verse expansion, chorus development, music production, creative audio projects, and professional song creation with simple integration, no coldstarts, and affordable pricing.

Features

Mureka AI Extend Lyrics continues existing song lyrics by generating the next lyrical line from the text you provide. It is designed for songwriting workflows where you want to expand verses, continue choruses, or explore lyrical ideas one line at a time.


Why Choose This?

  • Lyric continuation Extend existing lyrics with a generated next line that follows the tone and wording of your input.

  • Fast songwriting support Useful for verse expansion, chorus continuation, and breaking through writer’s block.

  • Simple workflow Paste your current lyrics and generate the next lyrical continuation with minimal setup.

  • Production-ready API Suitable for lyric-writing tools, demo workflows, and music ideation pipelines.

  • Low-cost generation Uses a simple fixed price per request.


Parameters

ParameterRequiredDescription
lyricsYesExisting lyrics used as the input context for continuation.

How to Use

  1. Paste your current lyrics — provide the lyric lines you want the model to continue.
  2. Submit — run the model to generate the next lyrical continuation.
  3. Review the result — use the generated line in your songwriting workflow or iterate again.

Example Input

The night falls softly on this empty street
The wind carries memories away from me
I hide the words I never got to say
Inside the last light before the break of day


Pricing

Just $0.002 per request.

Billing Rules

  • Each lyric extension request costs $0.002
  • Pricing is fixed per request

Best Use Cases

  • Verse continuation — Extend unfinished verses with a next-line suggestion.
  • Chorus development — Explore how a chorus might continue.
  • Songwriting ideation — Generate fresh lyrical directions from an existing draft.
  • Writer’s block relief — Get a quick next-line continuation to keep momentum.
  • Demo writing workflows — Rapidly test lyric variations during composition.

Pro Tips

  • Provide enough lyrical context for the model to follow the tone and theme.
  • Use clear rhythm and structure in the input when you want a more natural continuation.
  • Iterate multiple times if you want to compare different next-line options.
  • Use the generated line as a starting point, then refine it manually for final songwriting.

Notes

  • lyrics is required.
  • This model extends one line at a time per request.
  • Pricing is fixed at $0.002 per request.
  • The output is intended as a continuation of the provided lyrical context, not a full song section in one run.

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"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/mureka-ai/extend-lyrics" \
  -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

ParameterTypeRequiredDefaultRangeDescription
lyricsstringYes--Existing lyrics to extend.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayOutput values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction
data.modelstringModel ID used for the prediction
data.outputsarray<string | object>Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model.
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to poll for the prediction result
data.statusstringStatus: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2026 WaveSpeedAI. All rights reserved.