Turns text into narration and isolates speech from background noise in recordings.
Scoody model guide
Find models for generating video, creating keyframes, animating presenters, enhancing footage and working with speech.
121 models and tools in the guideVideo generation
77Choose a model for a new shot. Start with a prompt, a still image or a video reference. If composition matters, check whether the model accepts keyframes.
Video editing and upscaling
17These models work with existing clips. Some change the contents of a shot, while others improve resolution or remove the background. Use conventional editing for cuts and shot order.
Presenters and lip sync
17For a new presenter, choose a model that accepts a portrait or avatar. For footage you already have, use lip sync to match a new audio track.
Scripts and storyboards
3Turn a brief into a sequence of scenes, then create images for the key shots. The script sets the action and the images establish composition before video generation.
Voice and speech recognition
4Generate narration from text or transcribe a recording. Dubbing uses speech recognition and voice synthesis at different stages. Timestamped transcripts are useful for captions and finding moments in a video.
Voiceover, music and video search
Finds moments in videos from descriptions of what appears on screen, is spoken, or can be heard.
Generates music for video from a text description through the Gemini API.