Google's Vertex AI adds Lyria for text-to-music creation
Google's Vertex AI platform now offers a comprehensive suite of generative media models, accommodating video, image, speech, and music modalities, with the introduction of the text-to-music model Lyria.
Vertex AI introduces Lyria as a text-to-music model in preview, allowing enterprises to create high-fidelity audio that captures subtle nuances and delivers compositions across various musical genres. Warren Barkley, Senior Director of Product Management, stated, "Today, we're continuing to invest in generative media by adding Lyria, Google's text-to-music model, to Vertex AI in preview with allowlist. With the addition of music, Vertex AI is now the only platform with generative media models across all modalities – video, image, speech, and music. This means you can build a complete, production-ready asset starting from a text prompt, to an image, to a complete video asset with music and speech."
Additionally, Veo 2, an advanced video generation model, has received new editing and camera control features designed to facilitate content refinement and repurposing, offering creative teams enhanced control over video content. Barkley emphasized that these features assist teams in iterating faster, producing higher-quality content, and reducing post-production time and costs.
The Chirp 3 model, focusing on audio generation and understanding, introduces Instant Custom Voice and enhanced transcription capabilities. These improvements enable custom voice creation from minimal audio input and the ability to distinguish speakers in transcriptions. Furthermore, Imagen 3, a text-to-image model, now offers improved image generation and inpainting capabilities for enhanced object removal and seamless editing.
In alignment with Google's AI Principles, the deployment of these models includes safety measures such as digital watermarking, safety filters, and data governance. Google ensures content generated is backed by indemnification against third-party intellectual property claims. "Designing and developing AI to be secure, safe, and responsible is paramount. Consistent with our AI Principles, Lyria, Veo 2, Chirp 3, and Imagen 3 on Vertex AI were built with safety at the core," the company reported.
Lyria enables enterprises to enhance brand experiences and streamline content creation by generating customizable, royalty-free music tracks in a short span, facilitating accelerated production workflows. The model is particularly useful for creating soundtracks for marketing, product launches, or in-store experiences, allowing brands to produce music tailored to specific narratives and emotional connections.
Veo 2 further expands video editing capabilities with features such as inpainting, outpainting, and sophisticated cinematic techniques. These upgrades allow for seamless editing of unwanted elements from footage, adaptation to various formats, and the incorporation of advanced visual effects without requiring extensive expertise.
Chirp 3's new features aim to enhance audio applications by introducing tools like Instant Custom Voice and transcription with diarization. "Instant Custom Voice is now generally available through an allowlist," states the announcement, highlighting the opportunity for enterprises to forge consistent brand identities through personalized audio content.
Companies like Goodby Silverstein & Partners, L'Oreal Groupe, and Kraft Heinz are successfully leveraging these models to enhance creative processes and accelerate production timelines. "Dalí imagined a film so surreal, so untethered from convention, that it couldn't exist in his lifetime. Now, thanks to the astonishing capabilities of Veo 2 and Imagen 3, we've been able to help bring that vision to life—not as a replica, but as a reawakening. It's one of the most creatively thrilling things we've ever done," commented Jeff Goodby, Co-Chairman, Goodby Silverstein & Partners.
Thomas Ménard, Manager of AI Center Enablement, L'Oreal Groupe, expressed, "By integrating Veo and Imagen into our creative process, we're not just speeding up marketing content creation, we're changing how we approach creativity." Similarly, Justin Thomas, Head of Digital Experience & Growth at Kraft Heinz, noted a dramatic reduction in creative development timelines from eight weeks to just eight hours, underscoring significant cost savings and efficiency gains.
