{
 "slug": "room-tone-under-generated-voice",
 "name": "Room tone under a generated voice",
 "category": "sound",
 "group": "Voice",
 "media": [
  "video"
 ],
 "checked": "2026-11-13",
 "effect": "A generated line stops sounding generated between the words.",
 "use_when": "Text-to-speech voice-overs.",
 "phrase": "lay recorded room tone under every generated line, roll off the highs above 7 kHz, add light compression and a short room reverb",
 "pitfalls": [
  {
   "text": "Measured on 28 Oct 2026: a generated line drops to digital zero between words, -240 dBFS in the quietest 50 milliseconds; a recorded line never does. With a stand-in room tone the quietest moment rose to -67.7 dBFS.",
   "evidence": "measured",
   "source": "Director Chair field notes on motion graphics"
  },
  {
   "text": "The recipe is one studio's. Whether the result sounds natural is judged by ear, not by the meter.",
   "evidence": "practitioner",
   "source": "Director Chair notes on Video from code at Anfloy (Dima Bilous)"
  }
 ],
 "per_model": [],
 "external_refs": [],
 "licensed": [],
 "site_names": [],
 "related": [
  "voice-chain",
  "natural-sound-under-broll"
 ],
 "rights": "own-work",
 "evidence": "measured",
 "source": {
  "url": null,
  "note": "Own words from Director Chair notes on Video from code at Anfloy (Dima Bilous) and Director Chair field notes on motion graphics"
 },
 "body": "",
 "shown_with": null,
 "url": "https://directorchair.ai/sound/room-tone-under-generated-voice",
 "markdown": "https://directorchair.ai/sound/room-tone-under-generated-voice.md",
 "prompts": {
  "chat": "Give me a sound brief: what to record or pick, where it sits on the timeline, the levels, and what to check before export, for a short video about [your product], for [your audience]. The technique is room tone under a generated voice: a generated line stops sounding generated between the words. How it works: lay recorded room tone under every generated line, roll off the highs above 7 kHz, add light compression and a short room reverb. It is right for: text-to-speech voice-overs. Measured on 28 Oct 2026: a generated line drops to digital zero between words, -240 dBFS in the quietest 50 milliseconds; a recorded line never does. The recipe is one studio's. Be concrete: numbers, seconds and settings, no theory. Ask me one question first if something you need is missing."
 },
 "licence": {
  "code": "MIT",
  "text": "CC BY 4.0",
  "third_party": "Clips and card texts inside a \"licensed\" block belong to their makers and are shown with permission and credit."
 }
}