665,000+ skills indexed

LeeAeronCOMMUNITY

Explore all skills by this author →

Verified:GitHub

acestep-lyrics-transcription

Transcribe audio into timestamped lyrics using Whisper or ElevenLabs Scribe APIs.

Updated Aug 23, 2026

Search Tags:#transcription #audio #elevenlabs #srt #lyrics #lrc #openai whisper

One-click install

npx skills add https://github.com/LeeAeron/AceStep --skill acestep-lyrics-transcription-leeaeron

Or copy as Structured Prompt for Agent▼

Please help me install this Agent Skill.
Skill: acestep-lyrics-transcription
Source: https://github.com/LeeAeron/AceStep/tree/main/.claude/skills/acestep-lyrics-transcription
Command: npx skills add https://github.com/LeeAeron/AceStep --skill acestep-lyrics-transcription-leeaeron

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires curl, jq, python3, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of transcribing audio files into timestamped lyrics, making it easier to generate lyric files (LRC, SRT, JSON) for music and video projects.

Core Features & Use Cases

Audio Transcription: Converts spoken or sung audio into text with precise word-level timestamps.
Multiple Output Formats: Supports LRC, SRT, and JSON formats for compatibility with various applications.
Provider Flexibility: Integrates with both OpenAI Whisper and ElevenLabs Scribe APIs.
Use Case: You have a song in MP3 format and need an LRC file for a music video. This Skill can transcribe the song and generate the LRC file automatically.

Quick Start

Use the acestep-lyrics-transcription skill to transcribe the audio file located at /path/to/song.mp3 and save the output as an LRC file.

Frequently Asked Questions about acestep-lyrics-transcription

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I transcribe an MP3 audio file into timestamped lyrics?▼

To transcribe an MP3 into timestamped lyrics, you can use this Skill to process the audio via OpenAI Whisper or ElevenLabs Scribe APIs and automatically generate word-level timestamps for your music files.

Can I generate LRC and SRT subtitle files from audio transcription?▼

Yes, audio transcription can generate output in LRC, SRT, and JSON formats. LRC is typically used for music videos, while SRT is standard for video subtitles, ensuring compatibility across applications.

Do I need an OpenAI Whisper or ElevenLabs API key to transcribe audio?▼

Yes, you need an API key for audio transcription. This Skill supports API key configuration and management for both OpenAI Whisper and ElevenLabs Scribe providers to process your audio files.

How do I get word-level timestamps for transcribed song lyrics?▼

Word-level timestamps are generated by transcribing your audio through the integrated APIs. This Skill processes the audio to provide precise timestamp synchronization for each word within the output text.

What is the best way to convert a song to an LRC file for a music video?▼

The best way to convert a song to an LRC file is using an automated transcription tool. This Skill processes the MP3 audio and directly outputs an LRC file with timestamped lyrics for video projects.

Does this audio transcription method work with both OpenAI Whisper and ElevenLabs?▼

Yes, this transcription method works with both OpenAI Whisper and ElevenLabs Scribe APIs. It offers provider flexibility, allowing you to choose either platform to convert audio into timestamped text.

Related Skills

Explore More Design & Creative Skills→

openai-whisper

Transcribe and translate local audio files using the OpenAI Whisper CLI.

acestep-lyrics-transcription

Transcribe audio to timestamped lyrics in LRC, SRT, or JSON formats.

vikrant-project

here.now

Publish static websites and share private files via curl and jq.

whisper-cli

Transcribe local audio and video files into timestamped JSON transcripts using whisper.cpp.