Nodaro.ai Node Reference

Complete reference for all nodes available in the Nodaro.ai visual workflow editor.

Tip: Every node supports Presets — save a node’s configuration under a name and reload it in one click, with built-in factory presets plus your own custom ones (searchable, exportable/importable).

Not sure which model to pick? See Choosing Models — everyday vs premium tiers and a use-case → model table across image, video, audio, and text.

Quick Reference

Table of Contents

Input Nodes

Provide data to your workflow: text, images, video, audio, or external triggers. These are typically the starting points of any workflow.

Node Description When to Use
Text User-provided text input with variable support Provide prompts, descriptions, or text data to downstream nodes
List List of items, or a multi-column typed table, for batch iteration Batch process multiple prompts or subjects; grow into a typed table for multiple variables per iteration
Upload Image Upload or provide an image URL Source images for image-to-video, editing, or composition
Upload Video Upload or provide a video URL Source video for processing, effects, or transformation
Upload Audio Upload or provide an audio URL Source audio for TTS, lip sync, dubbing, or mixing
RSS Feed Pull content from RSS/Atom feeds Automated content pipelines from blogs or news sources
Web Scrape Scrape Google Search, web pages, RSS, Instagram, or TikTok (5 actors, dynamic credit cost) Data ingestion pipelines; seed generation workflows with live search results or social post metadata
Video URL Download video/audio from YouTube or other URLs Import video from YouTube, TikTok, Instagram, Facebook, X
Reference Audio Extract audio from YouTube or uploaded video Extract audio tracks for dubbing, remixing, or analysis
Webhook Trigger Trigger workflow via HTTP webhook endpoint Integrate with external systems, APIs, n8n, or Zapier
Schedule Trigger Trigger workflow on a cron schedule Daily content generation, recurring social posting
Telegram Trigger Trigger workflow when a Telegram bot receives a message Run pipelines from chat messages, photos, or videos sent to your bot

Parameter Nodes

Configure shared settings that feed into multiple downstream nodes. These control generation behavior.

Parameter picker nodes have a typed colored output pip — click it to see which downstream nodes are connected to this picker, manage connections (disconnect, focus, connect to a new consumer), and drag-reorder where applicable.

Generation parameters

Free-form or enum settings that feed AI / video / audio generation nodes via FieldMappings or direct text wiring.

Node Description When to Use
Tone Define tone/style for AI generation Set consistent tone across script and image generation
Style Guide Visual style reference text Maintain consistent visual aesthetics across generated assets
Provider Select AI provider and model Route generation to a specific model for downstream nodes
Scene Count Specify number of scenes to generate Control script generation output length
Duration Set target duration in seconds Define video or audio length for downstream nodes
Aspect Ratio Define video/image aspect ratio Set consistent dimensions (16:9, 9:16, 1:1, 4:5)
Motion Control motion intensity Adjust video generation movement (subtle/moderate/dynamic)

Picker nodes — Look family

Visual style, mood, color, atmosphere, and aesthetic pickers. Wire into an AI image/video node’s cinematography handle.

Node Description When to Use
Setting Pick from 63 settings across indoor/urban/nature/fantastical Establish where a shot takes place
Atmosphere Pick atmospheric conditions (fog, rain, smoke, …) from 40 entries Add weather, particles, and light scattering to a scene
Style Pick a visual style preset (cinematic, anime, oil-painting, …) from 48 entries Lock the overall aesthetic register
Color / Look Pick a color-grading look (warm, teal-orange, bleached, …) from 41 entries Set the chromatic signature of a frame
Mood Pick a mood (calm, tense, melancholic, …) from 50 entries Anchor the emotional tone of a generation
Photographer / Artist Pick from 67 photographers, directors, illustrators, painters Anchor in a recognizable creator-style canon
Aesthetic / Microtrend Pick a microtrend aesthetic (y2k, cottagecore, vaporwave, …) from 46 entries Tap into named visual subcultures
Era / Period Pick a historical era (1950s, ancient-rome, victorian, …) from 32 entries Set the chronological frame
Photo Genre Pick a photography genre (fashion-editorial, street, macro, …) from 46 entries Lock genre conventions
Backdrop Pick a studio backdrop (white-seamless, cyc-wall, gradient, …) from 40 entries Studio / product / portrait composition
Render Quality Pick a render-pipeline preset (raytracing, octane, unreal, …) from 24 entries Nudge toward CG/3D aesthetics
Composition Effect Pick a composition effect (bursting-through-frame, DoF, …) from 19 entries Compositional discipline
Post-Process Effect Pick a post-processing effect (vignette, grain, light-leak, …) from 18 entries Finishing-pass aesthetics
Action FX Pick environmental effects (multi-pick) from 72 entries Earthquake, lightning, explosion, falling-objects — scene-event prompt injection
Loop Subject Pick a loop subject (tunnel, kaleidoscope, vortex, …) from 35 entries Seamlessly-looped video content

Picker nodes — Camera family

Lens, format, motion, transitions, and character-driven effects.

Node Description When to Use
Camera Motion Pick from 71 camera motions; graph-aware startState/endState handles Set camera behavior (static, pan, dolly, zoom) for video generation
Lens Pick from 16 lenses (wide-angle, normal-50mm, telephoto, fisheye, anamorphic, …) Set focal-length character
Camera / Film Stock Pick from 31 camera/film formats (35mm, IMAX, super-8, polaroid, VHS, …) Specify recording medium
Transition Pick a cinematic transition (76-entry catalog, 8 categories, multi-pick + timing fields) Inject transition effects into AI-generated video clips (cross-dissolve, time-shift, morph, portal, glitch, etc.)
Character FX Apply a character-driven effect (57 entries, 5 categories) with target ref name substitution Animate transformations, fantastical powers, body modifications, or subject-bound auras on a named character

Picker nodes — Subject / Object family

Pose, material, animals, vehicles, weapons, props.

Node Description When to Use
Pose Pick a pose from 81 entries (standing, sitting, action, dynamic) Direct subject posture
Material Pick a material from 66 entries (silk, leather, metal, glass, marble, …) Set dominant surface/substance
Animal Pick an animal from 126 entries with descriptions Feature animals in a scene
Vehicle Pick a vehicle from 107 entries with descriptions Feature vehicles in a scene
Weapon Pick a weapon from 85 entries with descriptions Action / fantasy / sci-fi / period work
Held Prop Pick a held prop from 59 entries (smartphone, umbrella, bouquet, …) Add narrative texture to a portrait or scene
Furniture Pick a furniture piece from 78 entries across 9 categories Furnish an interior scene with a specific, well-described piece

Picker nodes — Multi-dim composed pickers

Pickers that combine multiple independent dimensions into a single descriptor.

Node Description When to Use
Framing Multi-dim: shot size + angle + coverage + composition + vantage (72 options across 5 fields) Per-shot framing direction
Lighting Multi-dim: time-of-day + style + direction (72 options across 3 fields) Compose a full lighting setup
Person Multi-dim: 21 attributes (type, age, ethnicity, regional aesthetic, build, face, hair, eyes, skin, …) — 547 options Casting brief / recurring-character generation
Styling Multi-dim: makeup + eyewear + headwear + hair + jewelry + nails + face-paint + fabric (262 options across 9 fields) Fashion-editorial / character continuity
Temporal Multi-dim: speed + freeze + direction + shutter (18 options across 4 fields) Time-based effects (slow-mo, freeze, reverse)
Exposure Settings Multi-dim: aperture + shutter speed + ISO (20 options across 3 fields) Photographic exposure-triangle direction

Picker nodes — Sound / Music / Voice

Music and voice-design pickers. Wire into Suno, Generate Music, Text-to-Audio, or ElevenLabs Voice Design.

Node Description When to Use
Music Genre Pick genre + subgenre + era for music generation Feed Suno Generate, Generate Music (MiniMax), Text to Audio
Music Mood Pick energy + emotion + vibe for music generation Feed Suno Generate, Generate Music (MiniMax), Text to Audio
Instrumentation Pick instruments + production style + vocal presence Feed music generators; flips MiniMax instrumental flag
Voice Character Pick age + gender + accent + timbre for ElevenLabs Voice Design Compose voice descriptions for Voice Design
Voice Delivery Pick pace + emotion + archetype for ElevenLabs Voice Design Compose voice descriptions for Voice Design

AI Text Nodes

Generate, transform, or extract text using AI models.

Node Description When to Use
Generate Script AI multi-scene script with cinematography Create structured video scripts with scene descriptions and camera directions
Generate Text LLM text generation from a prompt (selectable model, optional image/video/audio refs). Two outputs: full text and a ===NEXT===-split items fan-out list. Built-in + user templates; “Create N Image Nodes” fan-out Rewrite/transform text, caption media, brainstorm, or fan out N image prompts
QA Check LLM quality gate — scores text 0.0-1.0, returns pass/fail + reason Validate generated scripts or captions before they continue downstream
Transcribe Speech-to-text with diarization Convert audio to text with speaker identification and timestamps

AI Image Nodes

Generate, edit, and transform images using 20+ AI providers.

Node Description When to Use
Generate Image AI image generation from text (23 providers) Create images from prompts with style, aspect ratio, and quality controls; inpaint a masked region or refine a result in place
Edit Image (legacy API endpoint) Documents the legacy edit-image REST endpoint (upscale / remove-bg / nano-banana-edit). Editor users: use Upscale Image, Remove Background, or Modify Image instead. Reference for edit-image API calls; new workflows should use the dedicated nodes
Modify Image Transform an image with a text prompt (20+ providers) Prompt-driven editing: style transfer, inpainting, instruction edits
Upscale Image Increase image resolution (Recraft, Topaz) Enhance generated or uploaded images to 2K/4K/8K
Remove Background Strip the background to a transparent PNG (Recraft) Cut out subjects for compositing or product shots
Image to Image (legacy API endpoint) Documents the legacy image-to-image REST endpoint (20 providers). Editor users: use Modify Image instead — it consolidates all prompt-driven image transformation. Reference for image-to-image API calls; new workflows should use Modify Image
Generate Mask Text-prompted segmentation mask (Grounded SAM) Create a mask for inpainting from a description; passes image through for chaining
Image Critic Score an image on realism / character consistency / prompt adherence / anatomy / aesthetic / style-match via VLM QC pipeline gates, automated regeneration loops with modify-image, batch quality scoring
Describe Image Extract text description from image Auto-caption images, extract prompts from art, accessibility
Describe to Picker Analyze an image with a vision model → catalog-valid picker JSON (Person) to auto-fill a parameter picker Turn a reference photo into a Person casting brief; recurring-character setup
Reference Sheet Composite a turnaround / expression / full reference sheet from a character, object, or location Build a model sheet for consistency; export, or feed the clean panels into generators as a multi-image reference
Reference Board Generate a dense reference board (hero + metadata + panels + palette) in one AI pass from reference image(s); refine globally, with a mask, or re-roll Lock a subject’s look in one premium artifact to feed downstream for consistency

AI Video Nodes

Generate video from images, text, or other video using state-of-the-art models.

Node Description When to Use
Generate Video Unified video producer — text-only, image-to-video, first+last frame, reference mode, or video-edit (V2V) driven by which inputs are wired (VIDEO_GEN_PROVIDERS catalog); providers include VEO 3.x, Gemini Omni, Kling, Seedance 2, LTX 2.3, and more Animate images, generate from text, run reference-driven multimodal mode (Seedance 2, VEO 3.x), or edit existing video (Gemini Omni) — one node, all modes
Generate Video Pro Long-form video — auto-splits requests beyond a single segment’s 15s limit into multiple Seedance 2 segments and stitches them into one clip (Cloud edition only) One continuous clip longer than 15 seconds
Edit Video Pro Replace a span (min 4s, max 120s) of an existing video with newly generated content — Seedance 2 reference bridge, stitched back into the source (Cloud edition only) Reshoot or restyle a portion of an existing clip without regenerating the whole thing
Image to Video (legacy) Redirects to Generate Video; legacy image-to-video workflows auto-migrate on load New workflows: use Generate Video instead
Text to Video (legacy) Redirects to Generate Video; legacy text-to-video workflows auto-migrate on load New workflows: use Generate Video instead
Video to Video Transform video with text prompt Style transfer or content modification on existing video
Relight & Switch Relight + switch/composite driven by the source pixels (Beeble SwitchX) Relight a subject, swap/restyle a background, or composite via reference image + alpha mask
AI Avatar Talking-avatar video from a HeyGen avatar + script or wired audio Generate presenter or spokesperson videos; two speech modes (script+voice / wired audio)
Cinematic Avatar Prompt-driven generative avatar clip from 1-3 HeyGen avatar looks (no script/voice) Cinematic intros, teasers, and stylized character moments driven by a text prompt
Lip Sync Sync audio to character face Create talking head videos from portrait + audio
Video SFX Generate synced sound effects, foley, or ambience for a video (replaces existing audio) Add SFX or atmosphere to silent or AI-generated clips via Replicate’s mmaudio
Face Swap Replace face in video with reference image Character replacement and creative remixing
Speech to Video Generate video from speech (Wan 2.2) Create video driven by speech audio input
Motion Transfer Apply video motion to static character Transfer movement from reference video to character image
Extend Video Continue video generation with new prompt Extend VEO, Runway, or LTX 2.3 Pro video with new footage at the start or end; Seedance 2 Extend continues ANY video by URL with seamless trim-stitched audio+video
Video Retake Replace a time window of an existing video — audio, video, or both (LTX 2.3 Pro) Surgically fix a few seconds of dialogue, repaint a botched shot, or re-score a specific beat

AI Audio & Speech Nodes

Text-to-speech, voice processing, and audio generation using ElevenLabs and other providers.

Node Description When to Use
Text to Speech ElevenLabs TTS with 3 models, 46 languages Convert text to natural speech with voice selection
Text to Audio Generate ambient audio and sound effects Create SFX, ambient sounds, or background audio from description
Voice Extractor Isolate voice from mixed audio Remove background noise, extract clean vocal track
Audio Separation Separate any audio into stems (Demucs) Vocal/instrumental split or full stems on any (non-Suno) audio
Text to Dialogue Multi-speaker dialogue generation Create conversations with different voices per speaker
Voice Changer Revoice audio or a talking video Replace the voice in audio — or a whole video — preserving emotion and timing
Voice Changer Pro Replace each speaker’s voice independently in multi-speaker audio or video Re-voice multi-speaker recordings with per-speaker voice mapping (Cloud only)
Dubbing Translate audio preserving speaker identity Translate spoken audio to another language
Voice Remix Generate voice from natural language description Create custom voice from text description
Voice Design Design custom voices with full controls Create reusable voices with loudness, guidance, and quality controls
Forced Alignment Word-level timestamp alignment Get precise word timing for captions or animation sync
Generate Music AI music generation (MiniMax) — for Suno use the dedicated Suno nodes Create background music or full songs from prompts

Suno Music Nodes

Dedicated suite for music creation, editing, and manipulation powered by Suno AI.

Node Description When to Use
Suno Voice Create a custom voice persona from a recording Train a voiceId to sing on Suno Generate / Cover / Extend
Suno Generate Generate full song from prompt and lyrics Create complete songs with style, lyrics, and vocal control
Suno Cover Create cover version of existing song Re-record existing audio in a new style or voice
Suno Extend Continue/extend existing Suno track Add more content to a Suno-generated track
Suno Lyrics Generate song lyrics from prompt AI-write lyrics with structure (verse, chorus, bridge)
Suno Separate Separate vocals and stems Extract vocal/instrumental or full 12-stem separation
Suno Music Video Generate music video for track Auto-create visual accompaniment for Suno audio
Suno Mashup Blend two tracks together Combine two audio tracks into a mashup
Suno Replace Section Replace section of track Re-generate a specific time range within a track
Suno Style Boost Enhance style of lyrics Improve and refine style text for better generation
Suno Add Instrumental Add instrumental to vocals Generate backing track for vocal-only audio
Suno Add Vocals Add vocals to instrumental Generate vocals for instrumental-only audio
Suno Convert WAV Convert MP3 to high-quality WAV Get lossless audio from Suno output
Suno Upload Extend Extend non-Suno audio via Suno Continue any uploaded audio using Suno’s generation

Video Processing Nodes

FFmpeg-based video manipulation.

Node Description When to Use
Combine Videos Concatenate videos with transitions Join multiple clips with ~50 FFmpeg xfade transitions: cuts, fades, dips, wipes, slides, irises, slices, reveals, covers, blurs, and zooms
Assemble Narrated Video Fit N ordered (clip, voice) blocks into one MP4 Audio-led narrated-video assembly: short voice centers over its clip with padding, long voice slows the clip (capped, then holds); audio is never cropped
Resize Video Crop, pad, or stretch to target aspect ratio Reformat video dimensions for different platforms
Social Media Format Auto-format for platform specifications Prepare video for Instagram, TikTok, YouTube, etc.
Trim Video Cut video to start/end times Extract specific sections from longer video
Extract Frame Pull a single still frame as a PNG Capture last frame for i2v chaining, thumbnails, or reference stills
Image Collage Composite N images into one 2K/4K image Tile a batch of images into a smart (justified) or grid collage — mood boards, contact sheets, social grids
Video Upscale Upscale resolution (Topaz, VEO) Enhance video quality to 1080p, 4K, or 8K
Add Captions Generate and overlay captions on video Add subtitles, word-highlight, or karaoke-style captions
Adjust Speed Change playback speed (0.25x-4x) Create slow motion or time-lapse effects
Loop Video Repeat video for target duration Extend short clips by looping
Fade In/Out Add fade transitions to video Smooth intro/outro with black or white fades
Transcode Video Convert video codec and resolution Change codec (H.264/H.265), quality, or resolution
Manual Edit Open video in web editor Make manual adjustments in browser-based editor
Remove Audio Strip the audio track, output a silent video Mute a clip losslessly before adding new sound
Video Analysis Scene-by-scene breakdown for AI re-creation Reverse-engineer a video (or YouTube URL) into castable ≤8s scenes with prompt-ready descriptions, mode-tagged audio, and reusable entity slots

Audio Processing Nodes

FFmpeg-based audio manipulation.

Node Description When to Use
Split into Chunks Divide a video or audio file into equal-duration segments (2 CR) Batch transcription, per-scene processing, or chunked dubbing of long recordings
Merge Video & Audio Combine video with audio tracks Add voiceover, music, or sound effects to video
Extract Audio Demux a video’s audio track to MP3 Pull audio from a video for transcription, dubbing, or reuse
Trim Audio Extract section of audio file Cut specific time range from audio
Mix Audio Blend multiple audio tracks with levels Layer voice, music, and SFX with volume control
Combine Audio Concatenate audio tracks end-to-end, with per-segment trim Join clips sequentially (vs. Mix Audio’s layering)
Adjust Volume Change volume and add fade transitions Normalize, boost, or fade audio tracks
Audio FX Reverb / EQ / echo audio effects Place a dry voice in a room (reverb), telephone/megaphone, echo

Text Processing Nodes

Simple text manipulation utilities.

Node Description When to Use
Combine Text Concatenate text with custom separator Join multiple text outputs into one
Split Text Split text by delimiter into list Break text into items for batch processing

Video Composition Nodes

AI-powered video composition and rendering. Create professional video productions from assets and prompts.

Node Description When to Use
Compose Video AI scene-graph video composition from text Build track-based video from natural language description
After Effects AI-generated post-processing effects Apply color grading, vignette, grain, blur, letterbox to video
Lottie Overlay AI-placed timed Lottie animations over video Add confetti, particles, animated graphics at specific times
3D Title AI animated 3D text scenes Create cinematic 3D title cards with particles and lighting
Motion Graphics AI 2D motion graphics generation Create lower thirds, title cards, kinetic typography
Composite Multi-layer video compositing Picture-in-picture, split screen, overlay with blend modes
Render Video Finalize composition to video file Render any composition plan to final video output
Scene Cloud-only. Pipeline-managed scene container with shot list, camera, motion. Created by the Story → Video pipeline (Phase 1B.2). Populated by the Scene Director LLM in Stage 5; animated by the pipeline orchestrator in Phase 1C

Asset Nodes

Create reusable character, creature, object, location, and face assets with multiple variations for consistent generation across workflows.

Node Description When to Use
Character Asset Multi-variation character assets, built in the full-screen Character Studio (Resources / Identity / Visuals / Character) — or pick an existing character from your Library or the Public Gallery Define characters with expressions, poses, motions, lighting, structured Person + Wardrobe attributes, a trainable LoRA (Cloud), voice, and personality; or reuse a saved/community character
Animal/Creature Asset Animal or creature with angles, poses, variations, motion — built in the full-screen Creature Studio, or chosen from your Library or the Public Gallery Define recurring animals or creatures (free-text species, incl. mythical) for consistent scenes; or reuse a saved/community creature
Object/Props Asset Object or prop with angles, materials, variations — created new, or picked from your Library or the Public Gallery Define props with multiple viewing angles and material options; or reuse a saved/community object
Location Asset Environment with time/weather variations — created new, or picked from your Library or the Public Gallery Define settings with time-of-day and weather variations; or reuse a saved/community location
Create Face Facial asset for lip-sync and replacement Maintain facial identity across generated images and video

Output Nodes

Deliver results to storage, webhooks, or social media platforms.

Node Description When to Use
Save to Storage Export final asset to cloud storage Persist generated content to R2 cloud storage
Webhook Output Send result to external webhook URL Deliver results to external systems or APIs
Instagram Post Publish to Instagram Post images, reels, stories, or carousels
TikTok Post Publish to TikTok Upload video content to TikTok
YouTube Upload Upload to YouTube Publish videos or shorts with title, tags, privacy
LinkedIn Post Post to LinkedIn Share text, images, or video on LinkedIn
X Post Post to X/Twitter Share content on X (280 char limit)
Facebook Post Post to Facebook Share text, images, video, or stories
Telegram Post Send a message, photo, or video to Telegram Publish to a Telegram chat, channel, or group via a bot

Workflow Nodes

Build modular, reusable workflows with sub-workflow nesting.

Node Description When to Use
Sub-Workflow Input Define input ports for nested workflow Create reusable workflow entry points with typed ports
Sub-Workflow Output Define output ports for nested workflow Define what a sub-workflow returns to its caller
Sub-Workflow Embed another workflow as a node, with inline editing and breadcrumb nesting Compose complex pipelines from reusable workflow modules – create a fresh child or reference an existing standalone workflow
Component Embed a published Nodaro Component (versioned marketplace sub-workflow) with exposed settings Drop a community or personal published component into any workflow; configure its inputs and settings inline

Generative Pipelines

Multi-stage AI pipelines that generate an editable Nodaro graph from a single prompt. Cloud edition only.

Node Description When to Use
Story → Video Cloud-only. Variable cost (~30 cr in Phase 1A). Orchestrates Detection (Haiku) → Showrunner (Opus) → Script + Cast Coverage Critics (Sonnet) under approval gates. Generate a complete cinematic workflow from a single story prompt; review and approve at each stage

Utility Nodes

Helpers for debugging and workflow organization.

Node Description When to Use
Preview Display text, image, video, or audio in editor Debug and inspect intermediate results
Reduce Fan-in N upstream values into 1 via a strategy (pick-best-llm / concat / first-non-empty / count / vote / merge-json) Close a List fan-out — pick the best variant, count survivors, or merge JSON
Selector Pick item(s) from a list — 7 modes (item / range / list / random / modulo / predicate / named-key); two outputs: picked + rest Share a single selection across multiple consumers, route rejected items, or reach operators the edge selector doesn’t support
Sticky Note Annotated notes on workflow canvas Document workflow logic and leave notes for collaborators
Group Spatial container that aggregates children’s outputs by type Organize related nodes; fan out per-type arrays into list-aware consumers
Collect Aggregate multiple inputs into per-type arrays Merge outputs from many nodes into ordered per-type lists
Filter List Keep list items matching one or more conditions (AND/OR) Narrow a scraped or generated list before fan-out
Sort List Sort a list by value or field (text/number/date, asc/desc) Order items by score, date, or name
Deduplicate Remove duplicate list items by value or field Drop repeats from scraped or merged lists
Merge Lists Combine lists by concatenation or element-wise zip Join parallel lists; inject a shared value into every item
JSON Process Filter, project, and extract paths from JSON data Reshape scraped/API JSON; drill into nested payloads
Extract Field Pull a specific field or dot-notation path from upstream JSON Extract title, url, or a nested property from Web Scrape or JSON Process output
Router Split execution into named routes via radio, checkbox, or data-driven conditional rules Build branching workflows, A/B paths, or data-conditional pipelines
Teleport Send Broadcast a value on a named channel without a visible wire Declutter large canvases; share one upstream value with distant or multiple downstream nodes
Teleport Receive Receive a value from a Teleport Send on the same channel Pick up a wirelessly broadcast value anywhere on the canvas