Search results for Internal-Open-Access-Audio

Audio

OpenMOSS Releases MOSS-Audio: An Open-Source Foundation Model for Speech, Sound, Music, and Time-Aware Audio Reasoning

The model unifies speech, environmental sound, music, and temporal reasoning into a single architecture — and outperforms every open-source model tested on general audio benchmarks...

Audio

Oppenheimer unfiltered: rare recordings released to the public

Newly released audio interviews reveal a personal, reflective side of Robert Oppenheimer The post Oppenheimer unfiltered: rare recordings released to the public appeared first on P...

From Accra to Frankfurt: The African Audio Revolution Is Already Here | Ama Dadson

  Across the continent, African stories are reclaiming their voice through audio, technology, and a new wave of cultural builders. *** In a recording studio in Accra, a measured, l...

Open data: the benefits and challenges of sharing a precious resource

Laura Feetham-Walker of IOP Publishing is our podcast guest The post Open data: the benefits and challenges of sharing a precious resource appeared first on Physics World.

smol-audio: A Colab-Friendly Notebook Collection for Fine-Tuning Whisper, Parakeet, Voxtral, Granite Speech, and Audio F...

smol-audio Is the Audio AI Cookbook Practitioners Have Been Waiting For The post smol-audio: A Colab-Friendly Notebook Collection for Fine-Tuning Whisper, Parakeet, Voxtral, Granit...

The Sound of the Internet: What Meme Audio Reveals About Contemporary Listening Culture

For much of human history, societies have organized themselves around shared sonic experiences. Sacred chants, folk songs, military marches, opera arias, radio broadcasts, and symp...

Audiovisionen: Victoria Keddie und Nour Sokhon in der Berliner Zwingli Kirche

Unter dem Titel Audiovisionen begegnen sich in der KulturRaum Zwingli Kirche mit Victoria Keddie und Nour Sokhon zwei eigenständige Positionen experimenteller Klangkunst. Victoria...

Space Lab Free Audio Workshop Series

Local audio and vintage decor store Space Lab is hosting a series of workshops for those interested in diving into the world of High-Fidelity music and audio equipment. The post S...

Audeum, the world’s first audio museum, opens in Seoul

Audeum, the world's first museum dedicated entirely to sound, has opened across seven floors in Seoul, South Korea. Audeum, the world’s first audio museum, opens in Seoul

New In Radio – 04/2026

Es gibt eine neue Ausgabe von unserem New In Radio. Dieses Mal wieder mit einem sehr diversen Soundprofil. Hier gibt es den Stream.

GN Showcases Auracast at World Congress of Audiology, Releases Data on Hearing Loss Stigma

The company partnered with Ampetronic for a live music event in Seoul featuring a K-pop group with hearing loss to highlight audio accessibility.

Stability AI launches new audio models that can generate 6-minute music tracks

Three of the four models are open-weight, meaning they are free to download and build upon. Source

How Auracast is Changing Access to Live Theater

Experiences at two theaters in the UK show how Auracast can improve live theater accessibility by delivering clear, personalized audio directly to users’ devices, enabling greater...

Transforming deep-space signals into cathedral sound

A new immersive sound installation at Oulu Cathedral, Finland, brings the research of MIT astrophysicist and associate professor of physics Kiyoshi Masui into a striking sensory fo...

Making Space: The Work of Access in Experimental Music

David Byrne. Photo by Cora Wagoner*By Jeff Arnal Making Space: The Work of Access in Experimental Music  Reflections from Big Ears on Democracy and the Avant-Garde  Across mul...

In the Echo Chamber: resilience in a wartime economy

As if one podcast were not enough for a morning, let me offer you a second one. On this occasion, I am the guest on Read the full article...

Stability AI Releases Stable Audio 3: A Family of Fast Latent Diffusion Models for Audio Generation and Editing

Stability AI has released Stable Audio 3, a family of latent diffusion models for instrumental music and sound effects generation. The release includes open weights for the small a...

Audio Analytics: From Sound Capture to Edge AI Events

Not long ago, audio analytics meant offline processing of recorded clips to search for keywords, measure levels, or tag events after the fact. Today, the industry is moving more to...

Inside the Listening Room’s Sonance Sessions and the rise of deep listening culture

The post Inside the Listening Room’s Sonance Sessions and the rise of deep listening culture appeared first on Getaway Magazine.

🎧sp#06 – chris wilson: from music journalism to the cellar door

Music Technology Accessibility: How the Industry Is Opening Up to Disabled Musicians

For most people working in audio software, accessibility isn't the first thing that comes to mind when evaluating a DAW or controller. Music technology accessibility (the design pr...

NVIDIA and the University of Maryland Researchers Released Audio Flamingo Next (AF-Next): A Super Powerful and Open Larg...

Understanding audio has always been the multimodal frontier that lags behind vision. While image-language models have rapidly scaled toward real-world deployment, building open mod...