WavJourney
First page
Paper summary
Leverages LLMs to orchestrate audio generation models for compositional storytelling.
Ask this paper
01
LLM as composer: Uses an LLM to plan scene-level audio scripts, then dispatches sub-prompts to specialized TTS, music, and sound-effect models.
02
Explainable structure: Produces intermediate audio scripts that users can inspect and edit, giving creative control rather than opaque end-to-end generation.
03
Storytelling workflow: Demonstrates long-form coherent audio stories with speech, music, and ambient sound combined into unified scenes.
04
Agentic audio precursor: An early example of LLM-as-orchestrator for multimedia generation - a pattern that matured in 2024 multi-modal agent frameworks.