Tag
A guide on training a generative AI model for kick drum sounds using an old Linux desktop with only 6GB VRAM, making AI audio generation accessible with limited hardware.
WanSong is a pure diffusion-based music generation model that directly produces high-fidelity, multilingual songs up to 5 minutes long with dual stems (vocals and background music) in a single run, addressing challenges in efficient generation, long-form audio, and controllability.
Release of C++/GGML based implementations of Supertonic 3, MOSS-TTS, IndexTTS2, and Irodori-TTS in audio.cpp, capable of generating 10 hours of audio in 3 minutes on an RTX 5090.
Qwen-Music is a music generation model that produces high-fidelity songs with vocals, supporting text-to-music and cover song generation. It uses a novel Melody-Chain-of-Thought mechanism and achieves state-of-the-art results on 13 of 16 objective metrics.
A report on testing an AI pipeline that automatically generates a full podcast episode from a given topic without any manual editing.
This paper introduces Audex, a unified audio-text LLM from NVIDIA that achieves state-of-the-art performance across multiple audio and speech tasks while preserving strong text reasoning capabilities without regression.
This paper presents a text-to-music generation system that leverages reward conditioning, expert iteration, and preference tuning to improve audio quality within a 120M-parameter model, submitted to the ATTM Grand Challenge at ICME 2026.
Google's Gemini TTS now supports streaming audio generation, allowing developers to build voice applications that start speaking instantly without waiting for full audio output.
LLM Gateway Chat is a platform that provides access to multiple AI models for chat, image, video, and audio generation.
Zyphra releases ZONOS2, an open-source real-time TTS model with high-fidelity voice cloning, under Apache 2.0, available on Zyphra Cloud on AMD.
Introducing VoxCPM2, a completely free for commercial use, open-source multilingual voice synthesis model supporting voice design, cloning, and 48kHz high-quality output, ranked #1 on GitHub trending.
This paper introduces the Eisbach log-barrier, a parameter-free weight derived from the entropy of DiT output's spatial energy distribution, which when applied to LoRA fine-tuning of Stable Audio 3 improves musical diversity and thematic development without causing mode collapse.
JD Open Source releases JoyAI-Echo (Echo-LongVideo), a text-to-audio-video diffusion model capable of generating minute-level multi-shot videos with consistent character identity and voice, using DMD distillation for 7.5x speedup.
An open-source AI model that generates sound effects from vocal imitations and text descriptions, addressing the challenge of searching for specific sounds.
Google DeepMind released Magenta RealTime 2, an open music generation model for on-device streaming with low-latency control via text, audio examples, and MIDI.
DEMON presents a real-time diffusion engine that enables live musical performance by controlling the denoising process, achieving up to 12.3 decoder completions per second on a single RTX 5090. It introduces heterogeneous scheduling, shared mutable state, per-frame blending, and windowed VAE decode for responsive control.
A new AI music model has been released, with demos that sound surprisingly realistic.
Spotify is rolling out AI-powered features that let users generate personalized podcasts from prompts, schedule daily or weekly briefs, and ask questions about podcast episodes via a new Q&A feature for Premium users.
A 1-click launcher for Stable Audio 3 allows running the model on any computer without a GPU, including CPU-only systems, and is cross-platform (Mac, Linux, Windows).
Jordi Pons announces Stable Audio 3, a family of open-weight models for generating instrumental music and sound effects, supporting fast generation and editing on licensed audio.