Create realistic 4-8 second videos from text prompts using AI. Supports optional starting image and reference images for consistency, with synchronized audio.
Create videos from text descriptions or starting images using AI models. Specify prompts, duration, aspect ratio, and model parameters to generate custom video content.
Provides an MCP interface to the Prism Videos API, enabling character management, template browsing, generation status polling, and downloading completed video generations.
Enables users to stream or download YouTube video information and direct links via the Ytstream API. It supports geographic optimization and language selection for better download speeds and audio availability.
Retrieve your generated media from AetherWave gallery — images, videos, audio. Filter by type, favorites, or paginate results for agent workflows like reframing or mastering.
Search YouTube for videos or channels by query. Paginate through results using the next_page_token from the previous response to retrieve additional pages.
Generate videos from text prompts or images using Google Veo 3.1. Support image-to-video animation, reference images for consistency, and multiple models, resolutions, and durations.
Generate AI photos from uploaded face images using 150+ themed styles or custom prompts. Select gender and category to apply a theme or provide a custom prompt for personalized results.