Ask HN: Are there AI models for generating sounds based on a text and reference?

Title: Ask HN: Are there AI models for generating sounds based on a text and reference? Source: hackernews Current audio generation workflows lack standardized multimodal support for simultaneous text prompts and reference audio inputs. While text-to-image models utilize image conditioning for style transfer, audio models primarily rely on unidirectional text-to-audio or audio-to-text pipelines.