Photo Credit: Google
Google has announced it is adding its text-to-music model Lyria to Vertex AI. Vertex AI is now the only generative AI platform with models across all modalities—video, image, speech, and music.
Vertex AI can now build a complete, production ready asset starting from just a text prompt, to an image, to a complete video featuring both music and speech. The model was also updated with Veo 2, an advanced video generation model to allow video to be refined and repurposed with precision. It also includes updates to Chirp 3, a groundbreaking audio generation and understanding model.
Chirp 3 can create custom voices with just ten seconds of audio input. It allows Vertex to weave AI-powered narration into existing recordings and adds a speech transcription capability that can distinguish between multiple speakers. Finally, Imagen 3 now has improved image generation and inpainting capabilities for reconstructing missing or damaged portions of an image.
Google says in alignment with its AI Principles, the development and deployment of Lyria, Veo 2, Chirp 3, and Imagen 3 on Vertex AI prioritizes safety and responsibility with built-in precautions like digital watermarking via SynthID, safety filters, and data governance.
Lyria produces high-fidelity audio from just a text prompt. The model can be used to create soundtracks for marketing campaigns, product launches, or immersive in-store experiences—all tailored to brand identity. Lyria enables companies to create sonic branding that resonates with a target audience to foster brand recall.
For video production, podcasting, and digital content creation, finding the perfect royalty-free music can be a time-consuming process. Lyria eliminates those hurdles by allowing content creators to generate custom music and tracks in just minutes—with control over the mood, pacing, and narrative of the final piece. Google says this can help improve production workflow and reduce licensing costs for projects that need lots of background music.
