audio-mixing

作者: google-gemini

將語音音頻與背景音樂混合成專業的廣播節目檔案。

npx skills add https://github.com/google-gemini/gemini-managed-agents-templates --skill audio-mixing

Audio Mixing

Combine the TTS speech audio and Lyria background music into a single, polished radio show file.

Embedded Script

python3 skills/audio-mixing/scripts/mix_audio.py --workspace ./workspace

Arguments

ArgumentDefaultDescription
--workspaceworkspaceRoot workspace directory

What it does

  1. Loads speech from {workspace}/audio/speech/speech.wav.
  2. Adds 3 seconds of silence padding to the end of the speech to prevent it from being faded out.
  3. Loads background music from {workspace}/audio/music/background.mp3 (if exists).
  4. Loops music to match speech duration, lowers volume to -18dB.
  5. Overlays speech on music with a 1-second music intro.
  6. Adds fade-in/fade-out.
  7. Exports as MP3.

Dependencies

  • pydub
  • ffmpeg (system)

Mixing Guidelines

ElementLevelNotes
Speech0 dBUntouched, full volume
Background music-18 dBBarely audible — subtle bed under speech

Transitions

  • Music fade-in: 3 seconds
  • Music fade-out: 5 seconds
  • Overall fade-in: 500ms
  • Overall fade-out: 2 seconds

Output

FilePathFormat
MP3 (distribution){workspace}/audio/final/ai_radio.mp3MP3, 192kbps

Fallback

If no background music exists, produces speech-only output with just fade-in/fade-out applied.

來自 google-gemini 的更多技能

greeter
google-gemini
一個友善的問候技能
official
code-reviewer
google-gemini
針對本地變更與遠端拉取請求的自動化程式碼審查,提供涵蓋正確性、可維護性及安全性的結構化分析。支援本地檔案系統變更(包含暫存與未暫存)及遠端 PR(依編號或網址),並自動透過 GitHub CLI 進行檢出。從七個面向分析程式碼:正確性、可維護性、可讀性、效率、安全性、邊界情況處理及測試覆蓋率。可執行選用的前置驗證套件(例如 npm run preflight)以提前發現問題。
official
review-duplication
google-gemini
在程式碼審查期間使用此技能,主動檢查程式碼庫中是否存在重複功能、重複造輪子或未能重複使用現有…
official
reconciliation
google-gemini
將已載入的費用與預先解析的發票資料庫進行比對,標記出金額不符、遺漏發票及商家不匹配等差異…
official
agent-tui
google-gemini
Main Agents: Do NOT use this skill directly. If you need to test the TUI, invoke the `tui_tester` subagent. Drive terminal UI (TUI) applications…
official
async-pr-review
google-gemini
當使用者想要開始非同步的 PR 審查、對 PR 執行背景檢查,或查看先前開始的非同步 PR 狀態時,觸發此技能…
official
ci
google-gemini
專為 Gemini CLI 設計的高效能、快速失敗的專業技能
official
critique
google-gemini
專長於審計和修復儲存庫腳本及 GitHub Actions 工作流程,以確保技術穩健性與安全性。
official