Narrate Video

Timed, synced video voiceover via Azure/Gemini TTS with ffmpeg mux — avoids the amix-silence and audio-cutoff traps.

Autor: feiskyer · feiskyer/video-skills

Działa po konfiguracji ★ 9.6/10

Narrate Video — Timed, synced video voiceover via Azure/Gemini TTS with ffmpeg mux — avoids the amix-silence and audio-cutoff traps.

Co robi ten skill

Adds a professional voiceover track to any video by analyzing scene transitions, writing timed narration segments, generating speech via Azure TTS or Gemini 3.1 Flash TTS, and muxing with ffmpeg while keeping audio and visuals in sync. Triggers on requests to add narration, voiceover, commentary, or dubbing to a video, including screen recordings and Chinese-language phrasings like "视频配音".

Raport z testu

Ran the real ffmpeg pipeline both ways on a 9s test clip: the naive baseline (single narration track dumped at the start) silently truncated the video to 4.5s via -shortest, while the skill's segment/adelay/amix(normalize=0) approach preserved the full 9s runtime with mean volume -17.6dB, right in the documented -25..-15dB target. Real friction: needs a paid Azure Speech or Gemini API key configured in ~/.narrate_video.env before it can actually synthesize speech.

Testowano: 2026-07-15 · Claude Code 2.x (agent harness)

Instalacja

git clone https://github.com/feiskyer/video-skills
mkdir -p ~/.claude/skills
cp -r video-skills/skills/narrate-video ~/.claude/skills/narrate-video

Komendy i przykładowe prompty

  • /narrate-videoTimed, synced video voiceover via Azure/Gemini TTS with ffmpeg mux — avoids the amix-silence and audio-cutoff traps.

Skille uruchamiają się na zwykłe polecenia — bez komend do zapamiętania. Po instalacji aktywują go prompty takie jak te (po angielsku):

  • Add a synced voiceover track to this screen recording using TTS
  • Dub this product demo without the audio track getting cut off early
  • This video needs narration timed to the scene transitions, add it please