ace step skills

18 tagged ace step, measured the same way as everything else here.

Browse within: ai-music 18music-generation 18skill 12gradio 6local-ai 6lyrics 6

timoncool/ACE-Step-Studio

Skill Claude CodeCodex

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.

327 8d ago A 62 tokens original MIT

acestep-songwriting

02

timoncool/ACE-Step-Studio

Skill Claude CodeCodex

Music songwriting guide for ACE-Step. Provides professional knowledge on writing captions, lyrics, choosing BPM/key/duration, and structuring songs. Use this skill when users want to create, write, or plan a song before generating it with ACE-Step.

327 8d ago A 55 tokens original MIT

acestep-thumbnail

03

timoncool/ACE-Step-Studio

Skill Claude CodeCodex

Generate song cover/thumbnail images using Gemini API. Creates artistic images suitable for music video backgrounds. Use when users want to generate album art, song covers, thumbnails, or background images for MVs.

327 8d ago A 45 tokens original MIT

claude-music-cover

04

AgriciDaniel/claude-music

Skill Claude CodeCodex

Creates cover versions and style transfers of existing songs using ACE-Step 1.5. Takes a reference audio file and generates a new version with different style, genre, or vocal characteristics while preserving musical structure.

45 20d ago A 47 tokens original MIT

AgriciDaniel/claude-music

Skill Claude CodeCodex

Generates music from text descriptions and lyrics using ACE-Step 1.5's Python API. Creates full songs with vocals, instrumentals, or both. Supports 50+ languages, 10-600 second duration, quality presets (draft/standard/high/max), and batch generation.

45 20d ago A 64 tokens original MIT

claude-music

06

AgriciDaniel/claude-music

Skill Claude CodeCodex

Music production suite using ACE-Step 1.5 via Python API. Routes /music commands for generation, cover, repaint, compose, analyze, export, enhance, random, and LoRA training. 50+ languages, up to 10-minute tracks, 48kHz stereo.

45 20d ago A 63 tokens original MIT