skills.rest
bilibili
bilibiliOFFICIAL
Explore all skills by this author →
WebsiteGitHub

carocut-media-audio

Generate voiceovers with Edge TTS and retrieve BGM/SFX for Remotion video projects.

120|12|Updated Mar 20, 2026
Search Tags:#timing#audio#tts#video-production#edge-tts#bgm#sfx
One-click install
npx skills add https://github.com/bilibili/carocut --skill carocut-media-audio
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: carocut-media-audio
Source: https://github.com/bilibili/carocut/tree/main/.opencode/skills/carocut-media-audio
Command: npx skills add https://github.com/bilibili/carocut --skill carocut-media-audio

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill streamlines the production of audio assets for video projects by generating voiceovers via TTS, and by automatically retrieving background music and sound effects, while producing timing data to synchronize audio with visuals.

Core Features & Use Cases

  • Voiceover generation: Generate TTS-based voice tracks with Edge TTS according to storyboard pacing.
  • BGM and SFX retrieval: Download royalty-free music and effects from Freesound to match mood and pacing.
  • Durations and timing: Produce durations.json for frame-accurate audio-visual synchronization in Remotion.
  • Incremental updates: Re-generate only changed VO segments while preserving overall timing when needed.

Quick Start

Run the audio workflow to generate voiceovers, fetch BGM and SFX, and produce durations.json.

Frequently Asked Questions about carocut-media-audio

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate AI voiceover generation and BGM retrieval for Remotion video projects?▼

Automate AI voiceover generation and BGM retrieval by using Edge TTS for voice tracks and fetching royalty-free music and SFX from Freesound, outputting a durations.json file for frame-accurate audio-visual synchronization in Remotion workflows.

How does durations.json work for synchronizing TTS audio with Remotion storyboards?▼

The durations.json file works by mapping generated voiceover, BGM, and SFX timings to storyboard pacing, ensuring frame-accurate audio-visual alignment within Remotion video production workflows.

Can I use Edge TTS to generate voiceovers that match specific video pacing and durations?▼

Yes, you can use Edge TTS to generate voiceovers that match video pacing by producing timing data that aligns audio segments with specific storyboard durations for Remotion projects.

How do I update changed voiceover segments without losing overall audio timing in video production?▼

Update changed voiceover segments without losing overall audio timing by using incremental updates, which re-generate only the modified VO segments while preserving the existing durations.json synchronization data.

What is the best way to get royalty-free background music and sound effects for automated video workflows?▼

The best way to get royalty-free background music and sound effects for automated video workflows is by retrieving audio assets from Freesound, matching them to project mood and pacing automatically.

Do I need external dependencies to generate frame-accurate audio synchronization for Remotion?▼

No external dependencies are required to generate frame-accurate audio synchronization; the skill modularly retrieves assets and produces durations.json natively for Remotion video workflows.

Related Skills

Explore More Design & Creative Skills→
arm2armarm2arm
4

manim-tts-narration

Generate per-scene German TTS narration with espeak-ng and merge audio into Manim videos.

Community
Intermediate
phamhuutri108phamhuutri108

remotion

Generate Remotion walkthrough videos from Stitch projects with transitions and overlays.

Community
Advanced
patrickhaahrpatrickhaahr

remotion-best-practices

Enforce Remotion best practices for React-based video projects.

Community
Intermediate
PlayableIntelligencePlayableIntelligence
307

game-audio

Generate procedural BGM and SFX with the Web Audio API.

Official
Advanced