ElevenLabs Adds Nano Banana Pro Model to Image and Video Platform.

ElevenLabs announced on LinkedIn that Nano Banana Pro is now available in its Image & Video offering, marking the AI audio company's latest move into visual content generation. The model brings studio-quality precision, improved text rendering in images, and support for up to 4K resolution.

While ElevenLabs built its reputation on voice synthesis and audio AI, the company has been steadily expanding into adjacent creative tools. The platform now offers image and video generation alongside its core speech synthesis capabilities, positioning itself as a broader creative suite rather than a pure audio play.

The new model addresses several common pain points in AI image generation. According to ElevenLabs, Nano Banana Pro delivers studio-quality precision and control, handles localized and legible text within imagery, incorporates real-world knowledge, and supports resolution up to 4K.

Text rendering has been a persistent challenge for image generation models, often producing garbled or illegible characters when users request text elements in images. The emphasis on "localized and legible text" suggests ElevenLabs is tackling this directly, though the company has not released detailed benchmarks or examples.

The reference to "real-world knowledge" is less clear. It may indicate training data that includes more accurate representations of physical objects, brands, or cultural contexts, though ElevenLabs has not detailed the model's training approach or data sources.

Nano Banana Pro is available now within the ElevenLabs Image & Video interface. The company is offering 22% off all image and video generation for Starter to Scale plan users through Monday, though it did not specify which Monday or provide an exact end date for the promotion.

ElevenLabs operates on a subscription model with multiple tiers. The discount appears aimed at encouraging existing voice and audio users to test the visual generation features, expanding usage beyond the platform's core product.

ElevenLabs has been making aggressive moves beyond its original voice cloning and text-to-speech roots. The company recently released Scribe v2, a transcription model, and has been signing enterprise deals for conversational AI applications, including a partnership with Toyota and operations expansion in Korea.

The addition of advanced image generation puts ElevenLabs in more direct competition with dedicated visual AI platforms, though its strategy appears focused on offering an integrated creative toolkit rather than best-in-class standalone tools. For users already in the ElevenLabs ecosystem for audio work, having image and video generation in the same platform reduces workflow friction.

Whether Nano Banana Pro can compete with models from Midjourney or other specialized image generators remains to be seen. The company has not shared performance comparisons, user examples, or technical documentation for the new model. For now, the focus seems to be on convenience and integration for existing customers rather than disrupting the image generation market outright.