---
name: sound-narration-temporal-criticism
description: Critique speech, voice-over, acoustic space, music, silence, montage and duration through heard and seen relations; no mixing, timing execution or audio generation.
---

# Sound Narration and Temporal Criticism

Reuse narration-line, dialogue-design, voice-direction, sound-design, music-direction and editorial-design. Continuous normal-speed audiovisual observation is needed for judgments of rhythm, listening, vocal delivery, musical pressure and felt duration; use lawful Observer receipts only within their exact source and coverage.

Map speech identities and temporal positions before judging redundancy: narration, inner thought, camera address, remembered speech and story-world dialogue may share a voice. A subtitle is a text/time aid, not proof of exact audible words. ASR remains an uncertain transcription until verified.

For each interval, examine whether image and sound repeat, displace, contradict, foreshadow or withhold. Visible overlap can serve hindsight, self-indictment, irony or delayed recognition. Conversely, fluent explanatory narration may shield a scene from an encounter it has not dramatized.

Investigate offscreen world and listening perspective: what intrudes, what the character hears or ignores, what remains independent of the narrator, and how attention changes. Silence, absence of score and absence of ambience are distinct. Do not infer any of them from a script or waveform alone.

Judge a hold by carried attention, pressure, relation and aftermath across its actual lead, body and tail. A long take is not automatically profound, and a quiet interval need not visibly change. Cut and transition have meaning through adjacent events and sounds; planned seconds cannot certify measured effect.

Test an alternative picture/sound relation or semantic placement without executing it. State the function and cost, not an arbitrary shorter duration or voice-over percentage. Protect successful music, discomfort and silence; unavailable hearing yields an explicit unassessed sound judgment.

Read [evidence and independence](../artistic-review-council/references/evidence-method.md) before judging media. Use [comparative craft sources](../artistic-review-council/references/critical-traditions.md) when invoking theory or a film tradition; distinguish the cited author's view from your inference. Read the relevant production Skill for its intent and vocabulary, without adopting its authority or self-review as proof of success.

Separate observed fact, interpretation and proposed revision. Each material judgment needs a source/version, scene-local time or text locator, the specific expressive relation, its consequence for the viewer, the strongest alternative reading and a confidence limit. Describe success as carefully as failure. Missing sound or continuous playback narrows the claim; it does not license inferred boredom, emotion or musical effect.

Write criticism and candidates only within the requested review workspace. Do not write Canon, Media, approvals, production plans, Runtime, providers, compiler, schema, configuration or existing Skill contracts. A critic's recommendation never creates a production Gate, authorizes spending, or overturns a user's adopted asset. Technical findings go to human maintenance. Read-only tool declarations do not enforce a filesystem sandbox.

## Existing source reads

Use supplied originals first. For a necessary missing original, use only the existing read operations `work.get_work`, `script.get_script`, `episode.get_episode`, `scene.get_scene`, `shot.get_shot`, `asset.get_asset`, `media.get_media` or `context.build_context`. Tool declarations do not authorize database access in an offline review or production mutation.
