AI image generation from a text prompt. Generate album and single cover art, podcast and video thumbnails, social and campaign graphics, concept art, storyboard frames, product shots, and article illustrations. Returns one hosted still image as PNG or JPEG in square, portrait, or widescreen framing (1:1, 4:5, 9:16, 16:9, 21:9). Async by default: poll the returned pollUrl for imageUrl, or pass ?async=false to block.

AI video generation from a text prompt. Returns an 8-second 720p clip with native audio. Use for short-form video, b-roll, product shots, music-video visuals, social clips, and ads. Include sound cues (instruments, voices, weather, movement) since audio is generated from the scene; a silent scene renders near-silent by design. Async by default: poll the returned pollUrl for videoUrl, or pass ?async=false to block.

AI music generation from a text prompt. Creates a complete original song with vocals, melody, and full arrangement as a finished MP3, not a loop or preview. Describe genre, mood, instrumentation, and tempo, supply your own lyrics, request an instrumental, or pin a style tag. Use for soundtracks under video, release-ready artist tracks, podcast and game themes, and demo sketches. Async: poll songId until model_version leaves 'pending'.