The Codec is an independent publication covering the frontier of AI audio, from neural synthesis and voice cloning to generative music and real-time audio processing. We write for engineers, researchers, and builders working at the intersection of machine learning and sound.
We started The Codec because the best work in audio ML was scattered across arxiv papers, Twitter threads, and conference talks with no single place pulling it together for practitioners. Our goal is technical depth without academic gatekeeping.
We publish weekly. Our coverage spans original research analysis, technical deep dives, builder interviews, and expert commentary from practitioners shaping the future of audio.
Marcus Webb. Editor. Background in ML infrastructure and signal processing.
Priya Chandrasekaran. Research correspondent. Writes our technical deep dives and paper reviews.
Daniel Kang. Staff writer. Covers voice AI, audio generation, and production technology.
Contact: editors@thecodec.xyz · Advertise with us
Disclosure: All editorial content on The Codec is produced with the assistance of AI. Contributor names are pseudonymous editorial personas. Interviews and quoted material are conducted and edited using AI-assisted tools.