Tools

Google's latest image model with reference, grounding search, and thinking capabilities.

Premium image generation with reference and reasoning support.

State-of-the-art image generation with exceptional detail and artistic control.

High-quality image generation with photorealistic output.

Fast, cost-effective image generation for quick iterations.

Advanced image editing through natural language instructions.

Remove backgrounds from images with high accuracy edge detection.

Upscale images to higher resolution while preserving detail.

ByteDance's latest video generation model with high fidelity and motion quality.

Advanced video generation with standard and pro tiers. Supports text, image, reference, and multi-image input.

Google's video model supporting text, image, first-last frame, and reference input modes.

Alibaba's video model with native audio, 15s duration, narrative and lip sync.

Cost-effective video generation with fast turnaround and good quality.

Latest Kling model with standard and pro tiers for high-quality video generation.

Vidu's latest pro model for text and image to video generation.

1080p video generation from text or image input.

Natural-sounding text-to-speech with voice cloning support and multiple languages.

Generate sound effects from text descriptions with high quality.

Transform voice characteristics while preserving content and natural quality.

Extract text (OCR), structured data, or descriptions from images using AI vision models.

Drop-in passthrough to Kling's native API. Use your ThankYou key with Kling's exact request bodies — video, lip-sync, omni, custom elements, presets.