MikeTrendsTrends right now

Yhn BusinessPersonal Finance first seen 21 h ago, last 4 min ago, peak #2

Hackers ask: can AI generate sounds from text and reference?

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 sound effects from a text prompt combined with a reference audio sample. The poster wants tools analogous to image-generation models but for audio. Discussion is just beginning, with readers likely pointing to text-to-audio research such as AudioLDM, Stable Audio and similar systems.

Why now: There is growing interest in generative audio tools as text-to-image and text-to-video models mature.

Hacker Newstext-to-audio AI models

Open on hn →

Rank over time, top of the chart is #1. 75 snapshots from 21 h ago to 4 min ago.

Evidence

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