Nedimo: An Evidence-Grounded Multilingual Pipeline for AI-Generated Sleep Stories

A new arXiv paper (2610.40970v1) presents Nedimo, a multilingual pipeline for generating and narrating low-arousal bedtime stories that separates deterministic planning from large language model generation and enforces explicit loudness, loudness-range and true-peak limits on each saved audio file. The authors state that a recent active-controlled trial did not support narrated bedtime audio as a standalone treatment for sleep disturbance, and they translate that uncertain evidence into conservative engineering requirements, including a four-phase attention taper, structural and lexical validation, bounded error-aware retries and quarantine of unresolved outputs. No clinical efficacy is claimed; the system is positioned as a relaxation and attentional-support tool, with a prospective protocol proposed for testing sleep-onset effects.

arXiv:2610.40970v1 Announce Type: new Abstract: Generative audio systems can produce large libraries of personalized bedtime content, but ordinary media objectives retention, completion, and novelty are poorly aligned with the goal of supporting a transition toward sleep. Direct evidence for narrated bedtime audio in adults is mixed, and a recent active-controlled trial did not support such audio as a standalone treatment for sleep disturbance. We translate this uncertain evidence into conservative engineering requirements and present a multilingual pipeline for generating and narrating low-arousal sleep stories. The implemented prototype separates deterministic planning from large language model generation, represents content and delivery parameters explicitly, shapes each script through a four-phase attention taper, validates structural and lexical constraints, performs a bounded error-aware retry, and quarantines unresolved outputs. Provider-agnostic text-to-speech synthesis is followed by paragraph-aware joining, two-pass loudness normalization, and a publication gate that re-measures the saved, encoded file against fixed loudness, loudness-range, and true-peak limits. The product data model records stop position, replay, early abandonment, and completion while treating these events as ambiguous behavioral proxies rather than clinical outcomes. We contribute an evidence-to-requirement mapping, a traceable guardrail architecture with explicit acceptance thresholds, technical evaluation criteria, and a prospective protocol for testing sleep-onset effects. No clinical efficacy is claimed; the system is positioned as a relaxation and attentional-support tool whose benefit and possible reliance must be evaluated empirically.