skills.rest
ChatCut-Inc
ChatCut-IncOFFICIAL
Explore all skills by this author →
GitHub

voice

Generate and synchronize voiceovers and sound effects with video timelines.

751|69|Updated Jun 25, 2026
Search Tags:#text-to-speech#sound effects#video editing#voiceover#audio synchronization#voice audition#timeline retiming
One-click install
npx skills add https://github.com/ChatCut-Inc/agent-plugin --skill voice-chatcut-inc
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: voice
Source: https://github.com/ChatCut-Inc/agent-plugin/tree/main/claude/skills/voice
Command: npx skills add https://github.com/ChatCut-Inc/agent-plugin --skill voice-chatcut-inc

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps you create, place, and maintain voiceovers and sound effects without losing alignment between spoken content, visual timing, and the editing timeline.

Core Features & Use Cases

  • Text-to-Speech: Generate English, multilingual, or Chinese narration using curated ElevenLabs and Doubao voices.
  • Voice Audition and Selection: Filter and preview suitable voice presets before generating audio.
  • Video Sync: Map narration to confirmed visual segments, validate actual audio duration, and keep existing voiceover aligned after retiming edits.
  • Sound Effects: Search the built-in sound effects library first, then generate original custom effects when no suitable match exists.
  • Use Case: Create a polished product demo with segmented narration matched to screen actions, while preserving synchronization after timeline changes.

Quick Start

Use the voice skill to create and synchronize a professional voiceover for the current video timeline.

Frequently Asked Questions about voice

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

FAQPage Schema
How do I sync generated voiceovers with a video timeline?▼

To sync generated voiceovers, the system maps narration to confirmed visual segments and validates actual audio duration against the timeline. This ensures precise audio synchronization during video editing without manual adjustment.

Can I use text-to-speech for multilingual video narration?▼

Yes, the text-to-speech feature supports English, multilingual, and Chinese narration generation. You can select curated voice presets from providers like ElevenLabs and Doubao to match your video editing requirements.

How do I keep voiceover alignment after retiming edits?▼

To keep voiceover alignment after retiming edits, the system applies synchronization maintenance to preserve the original timing relationships. It checks timeline placement and validates audio duration so existing voiceovers stay matched to visual segments.

Does this tool search a sound effects library before generating custom audio?▼

Yes, the system searches a built-in sound effects library first to find matches. If no suitable sound effects exist, it then generates original custom audio, ensuring efficient SFX creation for your video editing workflow.

How do I audition and select voices for dubbing or replacement?▼

For voice audition and selection during dubbing or replacement, you can filter and preview suitable voice presets before generating audio. This requires specifying a concrete provider and voice preset for the text-to-speech process.

Related Skills

Explore More Design & Creative Skills→
liancheng-zcyliancheng-zcy
96

tts-voiceover

Generate 48kHz mono WAV voiceovers from text using VoxCPM2.

Community
Intermediate
Clos01Clos01
3

audio-jingle

Generate music, voiceovers, and sound effects as MP3 or WAV files.

Community
Advanced
outscaloutscal
62

script-writer-personality

Generate personality-driven educational video scripts from research and story arc files.

Official
Advanced
anis-marrouchianis-marrouchi

motion-animation

Integrate Framer Motion with Remotion for frame-synced animations.

Community
Intermediate