---
title: Generative audio
slug: generative-audio
qid: 
snapshot: enwiki-001345248243
content_hash: 
license: CC BY-SA 4.0
source: https://en.wikipedia.org/w/index.php?oldid=1345248243
tags: [103076333, 23603337, 24339681, 24745122, 26220375, 26441620, 34200192]
---

# Generative audio

> [!note] Provenance
> Snapshot `enwiki-001345248243` · content root `…`
> Derived from <https://en.wikipedia.org/w/index.php?oldid=1345248243> · Licensed CC BY-SA 4.0

Generative audio refers to the creation of audio files from databases of audio clips. This technology differs from synthesized voices such as Apple's Siri or Amazon's Alexa, which use a collection of fragments that are stitched together on demand. Generative audio works by using neural networks to learn the statistical properties of an audio source, then reproducing those properties.

Generative audio refers to the creation of audio files from databases of audio clips. This technology differs from synthesized voices such as Apple's Siri or Amazon's Alexa, which use a collection of fragments that are stitched together on demand. Generative audio works by using neural networks to learn the statistical properties of an audio source, then reproducing those properties. ==References==
