Audio Tech News Today

YuE2 is a new AI model that unifies symbolic and audio music generation to produce high-quality tracks. The system uses symbolic planning to convert user-provided lyrics and style prompts into an editable musical score. This process enables the generation of complete, fully produced songs featuring both vocals and instrumental accompaniment.

Apple today announced AirPods 5, featuring an open-ear design with industry-leading Active Noise Cancellation. The new earbuds also deliver significantly enhanced sound quality compared to previous versions.

Desert Ant Labs is launching a new frontier lab focused on developing fast, on-device AI models for audio, vision, and text. By running these small, specialized models locally, the company aims to deliver a faster and completely free alternative to traditional cloud-based AI services.

Jellyfin has released version 12.0, introducing crucial bug fixes for audio and video desync issues alongside improved EOTF processing and new Brainz integrations. The latest update for the open-source media server also highlights significant community contributions, including key development work by crobibero.

Developer iczelia has introduced Balrogg, a new lossless audio recompressor designed to optimize Vorbis and Opus files. The tool can reduce the file size of these specific formats by up to 15% without degrading the original sound.

A developer created the Aetheryte Radio to stream relaxing, unobtrusive ambient sounds from the video game Final Fantasy XIV to help maintain focus during work and gaming. The project explores various audio APIs and web streaming technologies, eventually expanding into a dedicated iOS app to overcome background playback restrictions.

StemDeck is a free, open-source AI tool that enables musicians and producers to locally isolate individual audio stems such as vocals, drums, and bass. Featuring a modern interactive interface, the platform streamlines creative workflows for practice, transcription, and remixing.

EasyEffects is being highly recommended by users for dramatically improving the poor audio quality of small laptop speakers, particularly on devices like Framework and GPD palmtops. By utilizing community-shared presets or custom Room EQ Wizard measurements, users can apply software-based equalization that transforms tinny hardware audio into acceptable sound. The tool's success has prompted calls for desktop environments like GNOME and KDE to natively integrate EasyEffects for seamless, system-wide audio tuning and loudness compensation.

Google has launched Gemini 3.5 Transcribe, a new tool designed to deliver more intelligent speech-to-text transcription. This latest release aims to significantly enhance audio processing capabilities for developers and users. The update highlights the ongoing integration of advanced AI models into everyday productivity workflows.

The AI audio startup landscape has evolved significantly from early hobbyist voice models like 15.ai to commercialized platforms like ElevenLabs. While ElevenLabs popularized a number-based naming trend and shifted toward enterprise solutions, many early pioneers eventually wound down their operations. Consequently, a new wave of companies like Fish Audio, Suno, and Udio has emerged to capture the underserved consumer and user-generated audio markets.

Engineers have optimized the serving infrastructure for the Qwen3-TTS model to achieve a p95 time-to-first-audio latency of under 50 milliseconds on a single H100 GPU. By processing 10 requests per second with this ultra-low response time, the optimization marks a significant step forward for real-time, high-throughput voice synthesis applications.

AliExpress is using silent WebAudio fingerprinting on its website to track visitors, which inadvertently breaks Bluetooth multipoint functionality. This hidden tracking method disrupts the ability of compatible headphones to maintain simultaneous connections with multiple devices.

Air Theremin is a browser-based virtual instrument that allows users to play a theremin in mid-air by waving at their webcam or tilting their smartphone. The application translates these physical gestures to control pitch, volume, and timbre, while also offering built-in features like note snapping, cave reverb, and audio recording.

IKEA's quirky product names often sound strange to native Swedish speakers and remain largely incomprehensible to international customers. Despite this linguistic barrier, the global furniture retailer's unique and fun naming strategy remains a beloved hallmark of its worldwide brand identity.

YC S26 startup Speko has launched as an OpenRouter for Voice AI that dynamically routes user sessions to the best-performing models. The platform addresses the industry's reliance on English-centric benchmarks by evaluating 61 speech and language models across 10 different languages. This ensures that non-English speakers consistently receive the highest quality voice AI experience.

The newly released Tea5767-Radio-Tuner is an open-source, custom PCB project that combines an ESP32 microcontroller with a TEA5767 FM tuner module. This compact DIY radio features a KY-040 rotary encoder for station selection, a PAM8403 amplifier for audio output, and a 0.96-inch OLED screen for visual feedback.

Eigendrum is a new interactive tool that allows users to draw custom shapes and instantly hear them played as drums. Rather than relying on pre-recorded audio samples, the application uses finite element analysis to calculate real vibration modes directly from the drawn outline.

Eigendrum is a new interactive application that allows users to draw custom shapes and instantly hear them played as drums. Instead of relying on pre-recorded audio samples, the tool uses finite element analysis to calculate the real vibration modes of the drawn outline. As a result, every unique shape produces its own distinct, procedurally generated drum sound.

Audio platform creator Dr. Ir. Stéphane Pigeon shares his personal journey of overcoming tinnitus by embracing the condition, which ultimately made the ringing disappear. In the accompanying video, he discusses his deep passion for acoustics and the development of his popular sound generation app, myNoise.

A new video explores the unique and nightmarish soundscape of the acclaimed video game Hyper Light Drifter. The feature details the extensive three-year development process behind the game's audio, which required countless revisions to perfect.

ComfyUI now features day-zero support for MiniMax H3, an open-weights omni-modal video model that generates 2K resolution video with native stereo audio. Thanks to significant optimizations, this powerful model can be run locally on accessible consumer hardware like a 3060.

CodePen has officially launched version 2.0 in a massive update that its creator describes as their largest personal career accomplishment. This new iteration required significantly more development effort than the original platform. Detailed information about the extensive technical changes can be explored in the newly released Why 2.0 podcast.

Hacker Public Radio is a community-driven podcast that releases new episodes every weekday. The show relies entirely on listener contributions to cover a wide variety of topics tailored to hackers and technology hobbyists.

A new open-source project called Audio-Cassette-Simulation enables users to replicate the authentic audio profiles of vintage cassette tapes. By leveraging the FFmpeg multimedia framework, the tool provides an easy way for audio enthusiasts to apply retro analog effects and warmth to their modern digital recordings.

In a new video, the speaker argues against succumbing to the fatalistic black pill mindset, urging viewers to reject technological doomerism as the world rapidly accelerates. Rather than feeling like passive observers while the future careens out of control, the presentation encourages individuals to reclaim their agency and actively shape tomorrow.

Max Studio Tools is a new open-source collection of C++ digital signal processing modules for Max/MSP and Ableton Live. The project provides essential virtual studio gear as externals for audio production and music creation. Developers can access the source code and contribute to the project via its GitHub repository.

Screenpipe is a newly launched YC-backed tool that continuously captures local screen and audio data to provide persistent, searchable context for AI agents. It prioritizes user privacy by offering customizable recording schedules, app filtering, and support for local or encrypted LLM processing. Developers are already utilizing its optimized performance to build personalized AI assistants and privacy-first enterprise workflow alternatives.

A new research paper introduces an automated system for monitoring honey bee colony strength using IoT audio sensors and recurrent neural networks. By converting hive acoustics into modulation tensorgrams, the machine learning model can accurately assess hive health. This innovative approach offers a promising technological solution for beekeepers and environmental scientists tracking pollinator populations.

The Transcribe.cpp project is a new initiative designed to simplify audio transcription while providing an interactive sandbox for tech enthusiasts. By allowing users to play around with the technology easily, it aims to make complex code integrations both straightforward and fun.

HMD has unveiled the Touch 4G, a compact hybrid phone featuring a touchscreen and up to 30 hours of battery life. The device bridges basic and smart phone capabilities with WiFi, Cloud Phone Service, and an Express Chat App for text, audio, and video calls.