Yhn BusinessPersonal Finance first seen 1 d ago, last 2 min ago, peak #2

Are there AI models that generate sound from text and reference audio?

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

A question on Hacker News asks whether AI models exist that can generate sounds from a text description combined with a reference audio sample. The discussion taps into growing interest in audio generation tools, following text-to-image and text-to-music systems like Stable Audio and AudioLDM. Commenters are weighing in with possible models, limitations, and how closely current tools can match a reference sound.

Why now: Interest in generative AI is expanding from text and images into audio, and developers are looking for practical text-and-reference-based sound tools.

Hacker NewsStable AudioAudioLDM

Open on hn →

Rank over time, top of the chart is #1. 18 snapshots from 5 h ago to 2 min ago.

Evidence

• Ask HN: Are there AI models for generating sounds based on a text and reference? · onemiketwelve · 34

API: https://socialmediatrends-api.osmike.com/v1/trends/1290658