Audio Sync Assembly

Build and revise FFmpeg-based video assemblies from scene renders and narration, including audio probing, scene retiming, pauses, trim/concat, setpts, atempo, phrase-to-visual cue alignment, and final timeline manifests. Use when narration length, visual beats, product moments, or scene boundaries must sync precisely.

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add saranambiar/hyperframes-video-agent-skills --skill audio-sync-assembly
Manual install
git clone --depth 1 https://github.com/saranambiar/hyperframes-video-agent-skills.git /tmp/hyperframes-video-agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/hyperframes-video-agent-skills/skills/audio-sync-assembly ~/.claude/skills/audio-sync-assembly

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Audio Sync Assembly

Use this skill when video timing must follow narration or when multiple rendered scenes need to become one final timeline.

## Source Of Truth

- Use the latest approved narration audio as timing source.
- Use scene renders as visual source.
- Use `templates/timeline-manifest.example.json` to record target timing.
- Do not infer timings from old final MP4s if source renders and audio clips exist.

## Probe First

For every clip:

- Duration.
- Frame rate.
- Resolution.
- Audio stream presence.
- Sample rate and channels.

Use `ffprobe` or this repo's media probe script once available.

## Sync Strategy

Choose the smallest timing intervention:

- Simple scene: retime whole scene to narration length with `setpts`.
- Scene with cue points: split into segments and retime each segment.
- Narration pause: insert silence and hold a frame.
- Replacement audio slightly longer: use small audio-only `atempo` only if preserving downstream sync matters more than raw duration.
- Product moment late/early: retime the segment before the product moment.

Read `references/ffmpeg-retiming.md` for command patterns.

## Phrase Alignment

Map spoken phrase starts to global timestamps when visuals depend on narration:

- Question cards.
- Product states.
- Chart points.
- Scene title reveals.
- CTA/logo arrival.

Caption timing and visual timing should share the same narration timeline.

## Assembly Order

1. Build synced scene segments.
Read the full skill on GitHub

Details

Skill name
audio-sync-assembly
Path
skills/audio-sync-assembly/SKILL.md
License
Apache-2.0
Repo updated
14 June 2026

FAQ

What does the Audio Sync Assembly skill do?

Build and revise FFmpeg-based video assemblies from scene renders and narration, including audio probing, scene retiming, pauses, trim/concat, setpts, atempo, phrase-to-visual cue alignment, and final timeline manifests. Use when narration length, visual beats, product moments, or scene boundaries must sync precisely.

How do I install the Audio Sync Assembly skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add saranambiar/hyperframes-video-agent-skills --skill audio-sync-assembly. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Audio Sync Assembly popular?

It lives in saranambiar/hyperframes-video-agent-skills, which has 48 GitHub stars and 0 forks.

Related skills

Captions and Music Bed

48

saranambiar/hyperframes-video-agent-skills

Generate, style, preview, and burn captions, and build music/percussion beds with ducking, loop/tail selection, fade-outs, and final silence. Use when captions are requested, captions are out of sync, subtitle style needs approval, background music competes with voiceover, or music must start/end at exact moments.

Images, Video & Audio

End to End Video Playbook

48

saranambiar/hyperframes-video-agent-skills

End-to-end video production workflow for coding agents using HyperFrames, FFmpeg, captions, audio sync, music beds, and render QA. Use when a user asks for a complete video, multi-scene edit, launch video, product/demo video, UGC-style edit, enterprise explainer, or final assembled MP4 from prompt/script/assets.

Images, Video & Audio

Hyperframes Scene Builder

48

saranambiar/hyperframes-video-agent-skills

Create and revise HyperFrames HTML video compositions with CSS, GSAP timelines, composition IDs, reusable components, render commands, and proof-frame validation. Use when an agent needs to build a scene, edit a composition, render HyperFrames output, or debug HyperFrames-specific scene behavior.

Frontend & Design

Apiyi Gpt Image 2 Gen

43

wuchubuzai2018/expert-skills-hub

图片生成技能,当用户需要生成图片、视觉信息图、创建图像、编辑/修改/调整已有图片时使用此技能。基于API易平台(https://api.apiyi.com/)的ChatGPT Image 2模型(gpt-image-2)的官方正式版图片生成服务。该模型支持精确的尺寸/画质控制(含4K),按token计费。与gpt-image-2-all(官逆版)不同的关键点:使用/v1/images/generations和/v1/images/edits端点;有显式size参数;有quality参数;按token计费;使用multipart/form-data上传参考图;b64_json为纯base64无前缀。

Images, Video & Audio

Apiyi Gpt Image 2 All Gen

43

wuchubuzai2018/expert-skills-hub

AI图片生成技能,使用ChatGPT最新生图 gpt-image-2-all,当用户需要生成图片、视觉信息图、创建图像、编辑/修改/调整已有图片时使用此技能。基于API易平台(https://api.apiyi.com/)的ChatGPT最新生图gpt-image-2-all模型(gpt-image-2-all)的图片生成服务,无需访问外网。该模型以 $0.03/张 按次计费,支持文生图、单图编辑、多图融合、自然语言改图,文字还原度高、中文提示词友好。尺寸通过prompt描述控制(无显式size参数)与NanoBanana2不同的关键点:无size参数,需在prompt开头描述尺寸;统一$0.03/张无分辨率阶梯;使用对话式端点/v1/chat/completions为主推。

Images, Video & Audio

Haizei Agnes Image Gen

43

wuchubuzai2018/expert-skills-hub

图片生成技能,当用户需要生成图片、视觉信息图、创建图像、编辑已有图片时使用此技能。基于Agnes AI官方API的Agnes Image 2.1 Flash模型(agnes-image-2.1-flash)的图片生成服务

Images, Video & Audio

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.