Appears on
Articles50
MOSS-Audio: An Open-Source Audio Understanding Model
Historically, AI audio models have focused primarily on Automatic Speech Recognition (ASR)—the straightforward conversion of spoken words to text. However, comprehensive audio understanding requires…
Soundcamp / Reveil 2026: Following the Dawn
Soundcamp / Reveil returns May 2–3 with its 13th edition : a 24+1 hour planetary broadcast that follows daybreak around the Earth through live environmental streams. More than a livestream, Reveil is…
AI Agents Enter the Studio: The MCP Turn in Audio
Anthropic’s Claude is starting to enter the audio workflow through new MCP connectors for Ableton and Splice, released among others for software such as Blender, Adobe Creative and Resolume Arena.…
Earshot: Listening as Evidence
Human rights investigation has long privileged the visible: satellite images, phone videos, CCTV, maps, and spatial reconstructions. Earshot works from the sonic, actually treating sound not as…
Modular Synthesizers Book
English edition of Modular Synthesizers , a book by Heiner Kruse, published by Radial Verlag / SynMag and dedicated to the vast world of modular synthesis. The book is available through several…
Inworld Realtime TTS-2, A Voice Model for Conversational Presence
Inworld AI has introduced Realtime TTS-2 , a new generation of its text-to-speech model designed specifically for real-time voice interaction rather than static narration. Released as a research…
Sonic Field Labs Is Now Online
Sonic Field has opened a new space for research, tools, archives, and experiments around sound, listening, computation, and emerging audio technologies: Sonic Field Labs . SFL expands our editorial…
AKOÚŌ: Operational Ears for Agentic Listening
Sonic Field Labs has launched AKOÚŌ , a new open repository for exploring how AI agents can listen. AKOÚŌ is a multimodal listening system and prompt library for agentic workflows. It works as a…
Sonic Detection: Listening as Investigation
Punctum books has published Sonic Detection: Necessary Notes for Arts and Performance , a new open-access book by Rebecca Collins and Johanna Linsley, available as (a free) PDF and in print. Moving…
Dance and Silence: Listening Through the Body
Bloomsbury Academic has published Dance and Silence: In Conversation , a new book by Vipavinee Artpradid and Petra Johnson that approaches silence as a field of embodied, ecological, choreographic,…
VOID Link Audio Connectors: Networked Audio Between Creative Tools
Structure Void has released Void Link Audio Connectors Bundle , a pay-what-you-want set of tools for streaming audio over a local network between creative…
AudioSpaces and the Geography of Sonic Memory
AudioSpaces is a simple idea with deeper implications: record a sound, pin it to a map, and let others encounter it in relation to the place where it happened. In a nutshell, the project is a mobile…
AI Voice Leaves the Turn-Based Era
Recent releases in AI speech suggest that voice technology is now way beyond the pipeline of speech-to-text → language model → text-to-speech . The new challenges are not only about producing…
The Listening Biennial: Listening as practice, care, and shared research
The Listening Biennial is a project that treats listening as something active, as a process of paying attention to things, places, ecologies, and forms of life that are often pushed aside. It brings…
Auditory Perception in Twentieth-Century Self-Narratives
Bloomsbury Academic published Auditory Perception in Twentieth-Century Self-Narratives: Oto-bio-graphical Subjects , a new book by Claudia Cerulo exploring autobiography through the ear. The book…
Stable Audio 3: Open, Generative and Editable Audio
Stability AI has released Stable Audio 3, with local weights, variable-length generation, and inpainting for studio workflows.
Sonic Field 2.0
Sonic Field now connects the journal with open lab experiments, early software, data analytics and research into machine listening, AI audio, soundscape generation, and sonic computation.
JASA opens June issue on acoustics, AI, ecology, and listening
JASA's June 2026 issue spans acoustics, listening, ecology, Bayesian methods, and generative or physics-informed AI for acoustic research.
Geographies of the Ear listens to Barcelona after Franco
Tania Gentic's Geographies of the Ear studies sound and language in post-Franco Barcelona, tracing echoic memory, colonial listening, migration, radio, punk, drag, and antigentrification protest.
Ableton Extensions SDK opens Live to JavaScript tools
Ableton's Extensions public beta introduces JavaScript tools for Live, with a local SDK that points toward set automation, audio import and render workflows, WebView interfaces, and offline analysis.