> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tryflowy.ai/llms.txt
> Use this file to discover all available pages before exploring further.
> ## Agent Instructions
> Flowy is a node-based AI creative platform: you generate images, video, audio, 3D and vector on an infinite Canvas, refine on the Studio timeline, and export or publish from the same project.
> Prefer the Flowy MCP server (https://mcp.tryflowy.ai/mcp) or the REST API at https://apis.tryflowy.ai/v1 for programmatic work. Install with `flowy mcp install` from the @flowy/cli package.
> Credits are workspace-scoped. Generations reserve credits on start and only deduct on success, so failed runs refund automatically.
# Tools
> One-shot AI tools for image, video, and audio. No canvas or nodes, just an input and a result.
Tools are Flowy's ready-made, single-purpose AI generators, upscaling, lipsync, face swap, voiceover, and more. Each one lives at its own URL outside any project: give it what it asks for, press generate, and get your result back. No canvas, no wiring nodes together.
## Tools vs. Canvas
Use a Tool when you have one clear job and one input: a photo to upscale, a clip to re-voice, a script to read aloud. Use the [Canvas](/canvas/nodes/overview) when you're building something with several connected steps, want to keep iterating non-destructively, or need a tool's output to feed straight into another generation.
Every Tool except one produces media: an image, a video, or an audio file. [Virality Analysis](/tools/virality-analysis) is the exception: it returns a structured report (a score and a list of fixes), not a file.
## Where to find them
Every Tool has its own URL `/{category}/{id}`, for example `/video/lipsync-studio` or `/image/upscaler`. You can also press ⌘ K from anywhere in the app to search for a tool by name, or browse the **Image**, **Video**, and **Audio** areas in the left sidebar, where Tools sit alongside the general-purpose model generator.
## Browse by category
### Image
Enlarge a photo 2x or 4x and recover fine detail.
Move an image's key light: direction, softness, brightness, color.
Swap a face into any photo in one run.
Replace a character in a photo while pose and scene stay put.
Grow a photo into a wider or taller frame: AI fills the new edges.
Virtual try-on: wear any outfit from a reference photo.
### Video
Enlarge a clip 2x or 4x, frame by frame.
Make any photo or clip speak a script or an uploaded voice track.
Transfer motion from a reference video onto your character.
Swap a face across every frame of a clip.
60 one-click camera moves, transformations, and effects from one photo.
Score your content before you post: returns a report, not media.
### Audio
Turn a script into studio-quality speech.
Swap the voice in a video or audio clip, timing untouched.
Translate a clip's speech into another language, same voice.
Every Tool shows a live credit estimate in its panel before you generate. The figures in these pages come straight from the current pricing table, but the backend's own pricing is always the source of truth.