Media.io API Supported Models: Complete List of Available AI Models & Capabilities
Kling Motion Control
Transfer precise actions, expressions, gestures, and full-body movements from a reference motion video to a static character image, with prompt-based scene control and high-fidelity consistency in timing and natural animation.
Kling 3.0
Pro model that generates video with native synchronized audio output, including dialogue, sound effects, ambient sound, and lip sync in supported languages, delivering premium quality with advanced physics, lighting, intricate motion, and superior cinematic control in multi-shot workflows.
Wan 2.6
Wan 2.6 generates coherent multi-shot videos up to 15 seconds, keeping characters consistent and synchronizing audio and visuals from text, images, or reference clips.
Nano Banana Pro
Google Gemini-3-Pro-Image-Preview: Advanced model excelling in complex reasoning, multi-turn editing, high-fidelity visuals, and legible multi-language text rendering.
Seedream 4.0
Unified model integrating image generation and editing for complex multimodal tasks, knowledge-based creation, and high-definition outputs up to 4K.
