跳到正文
TakoAPI
返回技能列表

acestep-lyrics-transcription

由 dumoedss 提供

AI & LLMs
575下载量由 clawskills.sh 提供
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Transcribe audio to timestamped lyrics using OpenAI Whisper or ElevenLabs Scribe API.

描述

该技能的功能

Transcribes audio files to timestamped lyrics using OpenAI Whisper or ElevenLabs Scribe. Outputs LRC, SRT, or JSON formats with word-level timestamps. Includes a post-transcription correction workflow to fix common misrecognition errors in sung lyrics.

Supports two transcription backends with word-level timestamps and includes a structured correction step that most raw transcription tools skip.

何时使用

  • Generating LRC files for music video rendering
  • Creating subtitles for song covers or demos
  • Extracting timestamped lyrics from foreign-language tracks
  • Syncing lyrics to audio for karaoke players
  • Correcting AI-generated transcriptions against original lyrics

示例工作流

输入

User asks: transcribe this Mandarin pop song to an LRC file

智能体
  1. 1

    Check if the active provider's API key is configured

  2. 2

    Run the transcription script with --audio and --language zh flags

  3. 3

    Read the output LRC file and the original lyrics reference

  4. 4

    Correct misrecognized words while preserving all timestamps

  5. 5

    Write the corrected LRC back to disk

输出

A timestamped LRC file with accurate lyrics saved to acestep_output/<filename>.lrc

前置要求

  • OpenAI API key (platform.openai.com/api-keys, billing required, ~$0.006/min) OR ElevenLabs API key (elevenlabs.io/app/settings/api-keys, free tier available)

安装

clawhub install dumoedss/acestep-lyrics-transcription

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接