recoup-lyric-video

Included with Lifetime

$97 forever

Make a lyric video — the song's words appearing on screen, timed to the audio, over a visual background. Use when the user says "lyric video", "make a video with the lyrics", "put the words on screen", "kinetic typography for [song]", or "animated lyrics for [song]". Transcribes the song to get word timings, generates or uses a background visual, and burns in the synced lyrics. Works with or without artist context.

Image & Video

What this skill does


# Lyric Video

Turn a song into a video where the lyrics appear in time with the audio. The job is
**timed text over a visual** — distinct from a featuring-artist clip (`recoup-short-video`)
or a no-text loop (`recoup-visualizer`).

Read `references/content-api.md` for the endpoints and async pattern,
`references/song-sourcing.md` for getting the audio, and `references/analyze-gate.md`
before claiming the result is done. (All ship alongside this skill.)

## Inputs

- **Song audio** (required) — see `references/song-sourcing.md`. No real audio → stop.
- **Background** (optional) — a generated visual, a supplied image/video, or the artist's
  aesthetic from `context/artist.md`. Generic mode: take the user's prompt or footage.
- **Lyrics** (optional) — if the user supplies an accurate lyric sheet, prefer it over the
  transcript for spelling; still use the transcript for **timing**.

## Steps

### 1. Get word-level timings

```bash
curl -sS -X POST "$BASE/content/transcribe" "${AUTH[@]}" -H "Content-Type: application/json" \
  -d "$(jq -n --arg u "$SONG_URL" '{audio_urls:[$u]}')" | jq '.segments'
```

`audio_urls` is an **array** (one or more public audio URLs). The response is
`{audioUrl, fullLyrics, segments:[{start,end,text}], segmentCount}`; `.segments` drives when
each line appears. If the user gave an official lyric sheet, align it to these timings rather
than trusting the raw transcript spelling.

### 2. Create the background

- **Context mode:** generate a visual on-brand with `context/artist.md` (or animate
  `context/images/face-guide.png`).
- **Generic mode:** generate from the user's prompt, or use footage they supply.
- A still works (loop it) or a slow motion clip via the `prompt`/`animate` video modes.

### 3. Burn in the synced lyrics

Use the edit endpoint to overlay text per timed segment over the background, then mux the
song for the full duration (see the edit ops + async pattern in `references/content-api.md`).
Keep text legible: large, high-contrast, inside safe margins, one line/phrase at a time.

### 4. Verify, then deliver

Run the analyze gate (`references/analyze-gate.md`) — check the words are readable, on
time, and not clipped. Regenerate any failing stage before presenting.

## Persist

In a workspace, save to `artists/{slug}/releases/{release-slug}/` (or `content/lyric-video/`)
and commit `{what}: {why}`. See `references/workspace-context.md`. No workspace → return
the URL.

## Guardrails

- **Timing comes from the transcript**, spelling from the official sheet when provided.
- **Don't reproduce third-party copyrighted lyrics** — this is the artist's own song; for
  covers or samples, confirm rights with the user.
- **Never fake the audio** (`references/song-sourcing.md`).

Files: 6

Size: 30.1 KB

Complexity: 50/100

Category: Image & Video

Source: https://github.com/recoupable/skills/tree/main/plugins/recoup-content/skills/recoup-lyric-video

Related in Image & Video

watch

Included

Watch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.

Image & Videoscriptsfeatured

physical-ai-defect-image-generation

Included

Use when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.

Image & Videoscripts

accelint-react-best-practices

Included

React performance optimization and best practices. ALWAYS use this skill when working with any React code - writing components, hooks, JSX; refactoring; optimizing re-renders, memoization, state management; reviewing for performance; fixing hydration mismatches; debugging infinite re-renders, stale closures, input focus loss, animations restarting; preventing remounting; implementing transitions, lazy initialization, effect dependencies. Even simple React tasks benefit from these patterns. Covers React 19+ (useEffectEvent, Activity, ref props). Triggers - useEffect, useState, useMemo, useCallback, memo, inline components, nested components, components inside components, re-render, performance, hydration, SSR, Next.js, useDeferredValue, combined hooks.

Image & Videoscripts

elevenlabs-agents

Included

Build conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs. Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT. Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflows or tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labs packages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication

Image & Videoscripts

humanizer

Included

Humanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.

Image & Videoscripts

generating-mermaid-diagrams

Included

Salesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. TRIGGER when: user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user wants PNG/SVG image output (use generating-visual-diagrams), or asks about non-Salesforce systems.

Image & Videoscripts