# NV GPU Buddy narration

All 13 chapters are narrated in the owner’s recorded voice using the existing local Qwen3-TTS environment. The continuous presentation lasts 4 minutes 11.46 seconds. Short 80–120 ms gaps between chapters preserve continuous pacing, with 280 ms visual transitions.

Canonical text is in narration/ and scenes.json. Pronunciation copies are in narration-spoken/; WAV masters and final speech MP3s are in audio/. The recording, model and voice-reference data remain local and are excluded from the published site.

The same owner-supplied Bensound SciFi track runs beneath speech at an 11 dB reduction, with the shared crossfaded music master and a final four-second fade. Speech and guide captions have controls; background music remains on beneath speech.

Automatic local transcription checked every chapter for missing or repeated text; no clip has clipped samples. These checks supplement listening review.

Player controls update: Quick review and the background-music toggle have been removed. Background music remains on beneath speech.
