Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions

TL;DR

Bagpiper is an 8-billion-parameter audio foundation model that uses rich natural language captions to understand and generate diverse audio content, enabling unified audio understanding and synthesis without task-specific training.

Contribution

Introduces Bagpiper, a novel audio foundation model that leverages rich captions for holistic audio understanding and generation, trained on 600B tokens, with a caption-then-process workflow for diverse tasks.

Findings

Outperforms existing models on audio understanding benchmarks.

Generates high-quality speech, music, and sound effects.

Achieves unified audio understanding and synthesis.

Abstract

Current audio foundation models typically rely on rigid, task-specific supervision, addressing isolated factors of audio rather than the whole. In contrast, human intelligence processes audio holistically, seamlessly bridging physical signals with abstract cognitive concepts to execute complex tasks. Grounded in this philosophy, we introduce Bagpiper, an 8B audio foundation model that interprets physical audio via rich captions, i.e., comprehensive natural language descriptions that encapsulate the critical cognitive concepts inherent in the signal (e.g., transcription, audio events). By pre-training on a massive corpus of 600B tokens, the model establishes a robust bidirectional mapping between raw audio and this high-level conceptual space. During fine-tuning, Bagpiper adopts a caption-then-process workflow, simulating an intermediate cognitive reasoning step to solve diverse tasks without task-specific priors. Experimentally, Bagpiper outperforms Qwen-2.5-Omni on MMAU and AIRBench for audio understanding and surpasses CosyVoice3 and TangoFlux in generation quality, capable of synthesizing arbitrary compositions of speech, music, and sound effects. To the best of our knowledge, Bagpiper is among the first works that achieve unified understanding generation for general audio. Model, data, and code are available at Bagpiper Home Page.