acestep-lyrics-transcription
由 dumoedss 提供
AI & LLMs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
User asks: transcribe this Mandarin pop song to an LRC file
- 1
Check if the active provider's API key is configured
- 2
Run the transcription script with --audio and --language zh flags
- 3
Read the output LRC file and the original lyrics reference
- 4
Correct misrecognized words while preserving all timestamps
- 5
Write the corrected LRC back to disk
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。