Veo 3.1 and advanced capabilities in Flow (blog.google)

Google is rolling out Veo 3.1 and a set of enhanced creative tools inside Flow, its AI filmmaking suite. Veo 3.1 upgrades Veo 3 with stronger prompt adherence, richer generated audio, improved audiovisual realism and finer texture detail when turning images into video. Flow’s existing generative features—Ingredients to Video (multi-image references), Frames to Video (start/end image morphs) and Extend (seamless long-shot continuation seeded from the last second)—now support audio, and new in-app editing tools let creators insert new elements that respect scene lighting and shadows or remove unwanted objects with background reconstruction. This matters because it shifts Flow from a purely visual prototype into a more complete audiovisual production tool, giving creators granular control over narrative, composition and sound. Technically, Veo 3.1 emphasizes fidelity to prompts and audiovisual coherence across generated frames, while Flow’s editing pipeline handles complex scene-level consistency (lighting, shadows, continuity) for insertions and removals. The features are experimental and iterative, but Veo 3.1 is available to developers and enterprises via the Gemini API, Vertex AI and the Gemini app—enabling integration into production workflows and third‑party tools.