AuDirector: A Self-Reflective Closed-Loop Framework for Immersive Audio Storytelling

TL;DR

AuDirector is a novel self-reflective framework for immersive audio storytelling that enhances coherence, expressiveness, and user interactivity through a multi-agent closed-loop system.

Contribution

It introduces a self-reflective, multi-agent framework with novel modules for character-aware synthesis, self-correction, and human-guided refinement in audio storytelling.

Findings

Achieves superior coherence, expressiveness, and fidelity over baselines.

Effectively integrates natural language feedback for interactive refinement.

Demonstrates improved audio quality through systematic self-correction.

Abstract

Despite advances in text and visual generation, creating coherent long-form audio narratives remains challenging. Existing frameworks often exhibit limitations such as mismatched character settings with voice performance, insufficient self-correction mechanisms, and limited human interactivity. To address these challenges, we propose AuDirector, a self-reflective closed-loop multi-agent framework. Specifically, it involves an Identity-Aware Pre-production mechanism that transforms narrative texts into character profiles and utterance-level emotional instructions to retrieve suitable voice candidates and guide expressive speech synthesis, thereby promoting context-aligned voice adaptation. To enhance quality, a Collaborative Synthesis and Correction module introduces a closed-loop self-correction mechanism to systematically audit and regenerate defective audio components. Furthermore, a Human-Guided Interactive Refinement module facilitates user control by interpreting natural language feedback to interactively refine the underlying scripts. Experiments demonstrate that AuDirector achieves superior performance compared to state-of-the-art baselines in structural coherence, emotional expressiveness, and acoustic fidelity. Audio samples can be found at https://anonymous-itsh.github.io/.