WA

WaveLLDM

A research model for efficient speech denoising and restoration using a compressed latent space via a diffusion approach—faster and less resource-intensive than many waveform-based methods.

Free plan available

About WaveLLDM

A neural audio codec (called FireflyGAN) that encodes audio into a compressed latent space and decodes it back. It is a latent diffusion model (LDM) that works in that latent space for tasks like denoising, audio inpainting (i.e. filling missing segments), and restoring degraded speech. The model achieves low Log-Spectral Distance (LSD) scores (≈ 0.48-0.60) indicating good spectral reconstruction. However, perceptual quality (as measured by WB-PESQ) is modest (≈ 1.62-1.71), and speech intelligibility (STOI) also moderate (≈ 0.76-0.78)—i.e. not yet on par with some state-of-the-art methods in those metrics.

Usage facts

Pricing

Free plan

Available

Likes

0

Views

0

Related tools

DE

Descript

https://www.descript.com

AI-powered audio and video editing platform

Free planFrom $15/monthFeatured
0 likes35 views
PL

Play.ht

https://play.ht

Versatile AI voice generation platform

Free planFrom $19/month
0 likes11 views
WE

WellSaid Labs

https://wellsaidlabs.com

Enterprise AI voice generation solution

Free planFrom $99
0 likes10 views
SP

Speechify

https://speechify.com/

text-to-speech tool that transforms written content into natural-sounding audio for faster, hands-free learning and productivity.

Free planFrom $11.58
0 likes19 views
ST

Stable Audio

https://stability.ai/

Generate custom music and audio from text prompts using Stable Audio—an advanced AI music generator from Stability AI.

Free planFrom $11.99
0 likes47 views
AU

Audioread

https://audioread.com/

Convert articles, PDFs, and emails into realistic, podcast-style audio using Audioread’s natural-sounding AI voices.

Free planFrom $14.99
0 likes10 views
AU

AudioShake

https://www.audioshake.ai

AudioShake uses AI to split songs into isolated stems—vocals, instruments, and more—for remixes, sync licensing, and localization.

Free plan
0 likes9 views
UD

Udio

https://www.udio.com

Udio is an AI music generator that creates full songs from text prompts complete with vocals, instruments, and customizable styles.

From $10
0 likes9 views
AU

Audiosocket

https://www.audiosocket.com

Audiosocket offers high-quality, licensable music for film, ads, YouTube, and games curated from real artists and composers.

Free planFrom $10
0 likes13 views
WO

Wondershare Filmora

https://filmora.wondershare.com/

A versatile video editor combining easy-to-use design with powerful AI tools—perfect for creators editing across devices and platforms.

Free planFrom $49.99 per year
0 likes10 views
SI

Singify

https://singify.fineshare.com/

Singify is an AI-powered music studio that transforms ideas into songs with tools like voice cloning, stem splitting, cover generation

Free planFrom $5.99
0 likes13 views
SU

Suno AI Bark

https://github.com/suno-ai/bark

An open-source text-to-audio AI model that creates expressive speech, music, and sound effects

Free plan
0 likes10 views