ElevenCreative
ElevenCreative is an AI-native creative workspace designed to generate, edit, and localize high-quality audio and video content within a single unified platform. It enables users to transform text into lifelike speech across more than 50 languages using advanced voice AI models, producing studio-quality narration for use cases such as audiobooks, ads, podcasts, and games. It combines multiple creative tools, including text-to-speech, music generation, sound effects, image and video creation, and editing features, allowing users to produce complete multimedia projects without switching between different tools. Users can add expressive, controllable voiceovers, generate captions, synchronize audio with video on an integrated timeline, and refine content iteratively through prompts or edits. ElevenCreative also supports localization workflows, making it possible to adapt content for different languages and markets in minutes while maintaining natural delivery and tone.
Learn more
Kinovi
Kinovi is a web-based AI media generation platform for creators and developers. Its browser-based Studio lets users select from a catalog of video, image, and audio models, submit prompts and supported reference media, and review generated results. The same model routes are available through a REST API, with documentation for authentication, task submission, status checks, uploads, webhooks, model inputs, and usage rates. A shared credit balance covers Studio and API requests; charges vary by model and settings, failed tasks are refunded, and purchased credit packages do not expire. Users can compare models and prices before choosing a workflow, while developers can automate generation and retrieve task results programmatically. Kinovi is suited to creative exploration, media production, and application workflows that need access to multiple AI generation models through one web interface or API.
Learn more
Donatello
Donatello is an all-in-one, browser-based AI studio for generating images, videos, music and voice content from prompts and creative controls. Its dedicated workspaces include text-to-image and image-guided creation, text- and image-to-video, vocal or instrumental music with optional lyrics, and voice tools such as text-to-speech, voice cloning and multi-speaker dialogue. The service is free and has no fixed lifetime, monthly or daily creation cap. Credits provide normal-priority generation; a lower-priority continuity queue may remain available when eligible free activities are unavailable, subject to fair-use, anti-abuse and capacity controls. Outputs from the current image, video, music and voice routes may be used commercially under Donatello's Terms. No paid subscription is required to start creating.
Learn more
EaseGen
EaseGen is a browser-based AI creative workspace for generating images and short videos from text prompts and visual references. Users can choose among image and video models, create new images from text, edit images using references, and make videos from text or images. Depending on the selected model, video workflows may accept multiple reference images, video, audio, or first and last frames, with model-specific controls for duration, resolution, aspect ratio, and audio. The workspace supports reviewing generation results, adjusting prompts and settings, viewing prior creations, and downloading outputs. Its examples and workflows address product and e-commerce visuals, advertising, social media content, posters, thumbnails, story concepts, and creative experiments. EaseGen has a free tier with basic models, plus paid monthly or annual subscriptions and credit packs; model access, generation volume, and credit costs vary by plan and workflow.
Learn more
