All articles tagged with #music generation
Google's Lyria 3 music-generation model arrives in the Gemini app, letting users 18+ generate 30-second AI tracks in multiple languages with lyrics, style, tempo, and vocals customizable; free tier caps output at 30 seconds while higher limits apply to AI Plus/Pro/Ultra; outputs include AI-generated album art and are watermarked with SnythID, serving as a basic AI-songs tool rather than a serious musical masterpiece.
Stability AI has released Stable Audio 2.0, an upgraded music-generation platform that allows users to create up to three minutes of audio via text prompt, with the option to upload an audio clip for analysis. While the tool is free and publicly available, the AI-generated music has been criticized for its soulless and weird vocals, as well as its tendency to make strange mistakes. Despite its potential for creating novelty songs, it lacks the human connection that defines music for many listeners.
Adobe has unveiled an experimental AI music generation and editing tool called Project Music GenAI Control, which can create music and other audio from text prompts and fine-tune them within the same interface. The tool aims to streamline the music creation process by eliminating the need to use external apps for editing. Users can input text prompts to adjust tempo, structure, intensity, and more, with the resulting music deemed safe for commercial use. This project is a collaboration with the University of California, San Diego and Carnegie Mellon University, and its consumer-facing UI may not be available for some time.
Adobe has announced Project Music GenAI Control, a new prototype AI tool that allows users to generate music using text prompts and edit the audio within Adobe apps. Developed in collaboration with the University of California and Carnegie Mellon University, the tool will offer integrated editing controls to customize AI-generated music. However, concerns arise regarding the sourcing of music for training and reference melodies. The release date for this tool is yet to be announced, but it signifies the ongoing advancements in AI technology for music and audio.
Google has updated its AI Test Kitchen app with a new "MusicLM" demo that allows users to describe any musical ideas and hear it come to life with AI. Users can specify instruments, vibe, mood, or emotion they're aiming for. The MusicLM generator casts the process of conditional music generation as a hierarchical sequence-to-sequence modeling task and generates music at 24 kHz that remains consistent over several minutes. The update is live on Android, and the AI Test Kitchen also gets a more text-heavy icon to replace the previous oven motif.