Multi-input composition
Combine photos, video clips, audio tracks, and Soul characters into one prompt.
Product · Mixed Media
Photo + video + audio + reference characters → one cohesive output. Mixed Media presets compose multiple input shapes into one render — for the workflows that don't fit a single endpoint.
Capabilities
Combine photos, video clips, audio tracks, and Soul characters into one prompt.
33 hand-tuned mixed-media presets covering common multi-input workflows.
Each preset routes to the model best suited for its input shape.
Pair a Soul character with an ElevenLabs voice in one config.
Define beats with stills and audio cues — render the connecting motion.
Save your own mixed-media setups as reusable templates.
Samples
Every clip below was rendered through Prototipal — no curation, no cherry-picked external content.
Related Apps