Skip to content
Get packs

Seedance Audio Director

Writes sound, dialogue, lip-sync and music direction for Seedance 2.0 video prompts

Source Download skill
Repository
Emily2040/seedance-2.0
Stars
8,008
Licence
MIT
Files
1 file

What it does

This skill teaches an AI agent how to plan the sound of an AI-generated video made with the Seedance 2.0 video model. Once installed, the agent lays out the speaker, the exact quoted dialogue, sound effects, music, ambience and silence, and checks timing so audio supports what is seen on screen. It also gives guidance on fixing lip-sync drift, mapping audio reference files to roles, and handling multiple speakers.

Great for

  • Creators writing Seedance 2.0 prompts that include dialogue, music or sound effects
  • Marketers building product ads that need timed sound cues
  • Anyone troubleshooting dialogue that falls out of sync in a generated clip

Skip it if

  • Editing or mixing real recorded audio, since the skill only writes generation direction and post-production notes
  • Cloning a real person's voice without rights clearance, which the skill itself says must be rights-cleared
  • Guaranteeing exact lip-sync results, since the skill states outcomes cannot be promised

Try asking

  • “Write the dialogue, sound layers and silence for a 6-second product reveal clip in Seedance 2.0”
  • “My two characters' lip-sync drifts when they talk back and forth, how do I fix the prompt?”
  • “Make @Audio1 control only the beat for a dance clip and tell me how to phrase it”
  • “Plan the ambience and sound effects for a tense drama scene with one line of dialogue”
Step-by-step guide: how to use Seedance Audio DirectorInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    seedance-audio.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip seedance-audio.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip seedance-audio.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Give the exact dialogue lines and speaker names up front so the agent can quote them unchanged
  • Keep one speaker per short clip and a stable camera when mouth accuracy matters
  • Check the referenced audio-guide and post-delivery files in the repository, since the skill points to them for detailed limits

What's inside

  • SKILL.md

Redistributed unmodified from Emily2040/seedance-2.0 under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.