Heartmula Transcribe Lyrics

Heartmula Transcribe Lyrics

Playground

HeartMuLa Transcribe extracts lyrics from audio files using advanced AI. Supports multilingual transcription. Ready-to-use REST inference API with best performance, no coldstarts, and affordable pricing.

Features

HeartMuLa Transcribe Lyrics is an AI-powered audio transcription model that extracts lyrics from music tracks. Upload a song and the model automatically recognizes and transcribes the vocal content into text.

Why Choose This?

• Automatic lyrics extraction Transcribes vocals from any music track into readable text.

• Simple one-input workflow Just upload an audio file — no additional configuration needed.

• Fast processing Get transcribed lyrics in seconds.

• Versatile audio support Works with various audio formats and music styles.

Parameters

How to Use

1. Upload your audio — provide the music track you want to transcribe.
2. Run — submit and receive the transcribed lyrics.

Pricing

Best Use Cases

• Lyrics Transcription — Extract lyrics from songs for reference or annotation.
• Music Production — Transcribe vocal recordings for editing and review.
• Content Creation — Get text versions of song lyrics for subtitles or captions.
• Music Analysis — Extract lyrics for study, review, or documentation.
• Karaoke Preparation — Generate lyrics text from audio tracks.

Pro Tips

• Use high-quality audio files with clear vocals for best transcription accuracy.
• Works best when vocals are prominent and not heavily mixed with instrumentals.
• Combine with HeartMuLa Generate Music to create songs then verify lyrics.

Notes

• Only audio is required.
• Output is a JSON object containing the transcribed lyrics text.
• Ensure uploaded audio URLs are publicly accessible.
• Transcription accuracy depends on vocal clarity and audio quality.

Related Models

• HeartMuLa Generate Music — Generate complete songs from lyrics and style tags.

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/wavespeed-ai/heartmula/transcribe-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

Response Parameters

Result Request Parameters

Result Response Parameters