Communitygithub.com

ace-step/ACE-Step-1.5

Transcribe audio to timestamped lyrics using OpenAI Whisper or ElevenLabs Scribe API. Outputs LRC, SRT, or JSON with word-level timestamps. Use when users want to transcribe songs, generate LRC files, or extract lyrics with timestamps from audio.

What is ACE-Step-1.5?

ACE-Step-1.5 is a Codex agent skill that transcribe audio to timestamped lyrics using OpenAI Whisper or ElevenLabs Scribe API. Outputs LRC, SRT, or JSON with word-level timestamps. Use when users want to transcribe songs, generate LRC files, or extract lyrics with timestamps from audio.

Works with~Claude CodeCodex CLI~Cursor
npx skills add ace-step/ACE-Step-1.5

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

What does ACE-Step-1.5 do?

Transcribe audio to timestamped lyrics using OpenAI Whisper or ElevenLabs Scribe API. Outputs LRC, SRT, or JSON with word-level timestamps. Use when users want to transcribe songs, generate LRC files, or extract lyrics with timestamps from audio.

Related Skills