Make a whiteboard explainer from your script
Make a whiteboard explainer or a whiteboard animation from your script: black line drawings on white, arrows and underlines that draw themselves on, and a voiceover. Here your agent builds it on a timeline from your script, scene by scene.
Use invideo for this when you want the drawings, the voice and the timing on one editable timeline, so a changed sentence means one new scene, not a new video.
invideo has no library of hand-drawn art and no drawing hand. Your agent makes the drawings with an image model, such as flux_2_lora.ballpoint_pen_sketch, and draws simple lines and arrows itself as shapes. For the classic hand that draws each picture, use a whiteboard tool, named at the end of this page.
Quickest path
Set up your agent first with invideo for AI agents. Then give it this prompt.
Make a whiteboard explainer in invideo from script.txt. One scene perparagraph. Black marker drawings on white, one per scene. Draw an arrowor underline on as each key word is said. Calm narrator. Show me thefirst scenes before you make the rest.In a chat app, you paste the script. In a terminal, the agent reads the file you name.
What you need
The script sets the length. The rest is style.
- The script, split into scenes, or permission for the agent to split it.
- The style: marker, ballpoint, colored pens, plain white or a board texture.
- A voice. The agent sends previews from
search_library. - The shape: 16:9 for most explainers.
Steps
The agent makes the first scenes, so you approve the style before it spends more.
Split the script into scenes
The agent splits the script into scenes, each with its line of narration and one picture to draw. It sees your yes on the scene list.
Voice the script
- The agent runs
find_modelswith "narration voice", picks one, and reads its inputs withget_model. A good pick iselevenlabs_text_to_speech.elevenlabs_tts_v4, with a voice fromsearch_libraryinelevenlabs_text_to_speech_voices. Your agent can search for others withfind_models. - It calls
generatewith the script asprompt, thevoice_idanddry_run: true, and tells you the price. - For a price of 1 credit or more it waits for your yes. Then it calls
generatewithmax_creditsset to that price and anidempotency_key. It gets a thread URL and, when the result lands, a sequence URL. It reads that URL withreadand never callsgenerateagain to check. - It prices
audio.transcriptwithdry_runon the voice's sequence URL and tells you the price. For a price of 1 credit or more it waits for your yes. Then it starts the transcript withmax_creditsset to that price, and calls again afterretry_after_sfor the words. It sees when each key word is said.
- The agent runs
Make the drawings
- The agent runs
find_modelswith "hand-drawn whiteboard image", picks one, and reads its inputs withget_model. A good pick for a sketch look isflux_2_lora.ballpoint_pen_sketch. For a character that stays the same across scenes, a good pick isnano_banana_2_1, which takesreference_images. Your agent can search for others withfind_models. - For each scene it calls
generatewith theprompt,aspect_ratio16:9 anddry_run: true, and tells you the price. - For a price of 1 credit or more it waits for your yes. Then it calls
generatewithmax_creditsset to that price and anidempotency_key, likescene-01. It gets a thread URL and, when the result lands, one image sequence URL per scene. It reads each URL withreadand never callsgenerateagain to check.
- The agent runs
Lay out the scenes
The agent makes a 16:9 timeline with
new_timelineand a branch withtimeline_history. It places the voice and the drawings withinsert_media, and fits each drawing to its line withtrim_clip. It sees a newstate_token.Reveal each drawing
The agent puts a plain white clip before each drawing and adds a
wipewithadd_transitionbetween them, so the drawing is wiped on. For a slow push-in, it adds azoom_xand azoom_ylane withadd_keyframe_laneand points withadd_keyframes. It sees the reveal incaptureframes.Draw lines on
For an arrow, a circle or an underline, the agent adds a shape with
add_shape, presetpath, an SVG path and a black stroke. In a second call,trim_shape_pathgrows the drawn part from nothing to the full line, timed to the word. It sees the line grow incaptureframes.Check, then export
The agent calls
capturemid-reveal and mid-line in each scene, andcheck_timeline. Then it callsexport. It sees an export card with statuscompleted.
The terminal version:
invideo gen models <project-url> --query "hand-drawn whiteboard image"invideo gen model <project-url> --model flux_2_lora.ballpoint_pen_sketchinvideo gen run <page-url> --model flux_2_lora.ballpoint_pen_sketch \ --dry-run -i prompt=@scene-01.txt -i aspect_ratio=16:9invideo gen run <page-url> --model flux_2_lora.ballpoint_pen_sketch \ --max-credits <price> --idempotency-key scene-01 \ -i prompt=@scene-01.txt -i aspect_ratio=16:9invideo gen models <project-url> --query "narration voice"invideo gen model <project-url> \ --model elevenlabs_text_to_speech.elevenlabs_tts_v4invideo gen run <page-url> \ --model elevenlabs_text_to_speech.elevenlabs_tts_v4 --dry-run \ -i prompt=@script.txt -i voice_id=<voice-id>invideo gen run <page-url> \ --model elevenlabs_text_to_speech.elevenlabs_tts_v4 \ --max-credits <price> --idempotency-key whiteboard-voice \ -i prompt=@script.txt -i voice_id=<voice-id>invideo status <thread-url> --waitinvideo notebook show <thread-url>invideo media audio.transcript <voice-sequence-url> --dry-runinvideo media audio.transcript <voice-sequence-url> \ --max-credits <price>invideo edit new <project-url> --name "Whiteboard v1"invideo edit show <edit-url> --jsoninvideo branch new <edit-url> --name scenes-1-2 --token <state_token>invideo edit show <branch-url> --jsoninvideo edit change <branch-url> --timeline T1 --token <state_token> \ --operations @scene-01.jsoninvideo edit show <branch-url> --jsoninvideo edit change <branch-url> --timeline T1 --token <state_token> \ --operations @draw-on.jsoninvideo edit capture <branch-url> --at 1,2.5,4 --out ./framesinvideo edit check <branch-url>invideo edit export <branch-url> --format video --quality 1080 --jsoninvideo status <card-url> --waitinvideo notebook show <card-url> --out ./outWhere each value comes from:
<project-url>comes frominvideo project new, and<edit-url>frominvideo edit new.<page-url>is a notebook page of the project, listed byinvideo notebook show <project-url>.<price>is each dry run's.estimated_credits.<voice-id>comes frominvideo library searchinelevenlabs_text_to_speech_voices. It works only withelevenlabs_text_to_speech.elevenlabs_tts_v4.<thread-url>is theurlthe paidgen runreturns.<voice-sequence-url>is the voice file thatnotebook showon it lists.<branch-url>is thebranch_urlthatinvideo branch newreturns.<state_token>comes frominvideo edit showon the URL the next command runs on:<edit-url>forbranch new, then<branch-url>, read again before each change.<card-url>is.sequences[0]of the export answer.invideo statuswaits but saves nothing.invideo notebook showsaves the video as./out/export.mp4, and the agent renames it.
Each ops file is the bare list of ops that --operations takes. The file behind @scene-01.json adds an underline shape. at_f and duration_f are frames at the timeline's frame rate.
[ { "op": "add_shape", "track": "V3", "at_f": 90, "duration_f": 150, "preset": "path", "d": "M 0 0 L 600 0", "width": 600, "height": 20, "x": 0, "y": 260, "fill": "#00000000", "stroke": { "color": "#111111", "width": 10, "cap": "round" } }]The file behind @draw-on.json goes in the next call and draws the line on. c14 is the new shape clip and <path-id> its path, both from invideo edit show after the first call. at_seconds counts from the start of the shape clip.
[ { "op": "trim_shape_path", "clip": "c14", "path": "<path-id>", "at_seconds": 0, "enabled": true, "start": 0, "end": 0 }, { "op": "trim_shape_path", "clip": "c14", "path": "<path-id>", "at_seconds": 1.5, "enabled": true, "start": 0, "end": 100 }]Cost and time
Edits and exports are free. Generation and transcripts cost credits. Paid stock costs a small credit charge, or one of your workspace's iStock licenses. Your agent runs a dry run first and tells you the price before it spends anything.
- Costs credits: one drawing per scene, the voice, and the transcript for word times.
- Free: the shapes, the line draw-on, the reveals, every edit,
captureandexport.
Your cost grows with the number of scenes and the length of the script. A short explainer takes under an hour. See Credits for prices.
If something goes wrong
Most problems are style drift or timing.
| Symptom | Fix |
|---|---|
get_model or generate refuses the model as not found | Models retire. Run find_models with the job in words, use the best match, and tell the person which model you used. |
audio.transcript refused with code: "not_found", or CLI exit 2 | The call named a media bin asset. Pass the voice's sequence URL from the generate result. |
invideo status --wait ends and the folder is empty | status does not download. Run invideo notebook show <card-url> --out <dir>. |
| Each drawing looks like a different artist | Use nano_banana_2_1 with the first approved drawing in reference_images. |
| The wipe goes through black | add_edge_transition fades from black. Use add_transition between a white clip and the drawing. |
| A line appears at once | trim_shape_path needs a point with end: 0 at the start and a later point with end: 100. If it still jumps, read timeline_catalog for trim_shape_path, and start a lane for the trim with create_shape_keyframe_lane. |
| The line draws at the wrong moment | Read the word times from audio.transcript and set at_f from them. |
trim_clip refused as stale | Read with get_timeline and use the edge's current frame. |
| Avoid: make every scene before approval | Instead: make the first scenes and show frames. |
Prompts to try
Each prompt is a real variation of this job.
Make a whiteboard explainer for our refund policy. Blue and black marker.Circle each number as it is said.Turn this script into a whiteboard video with one recurringcharacter, a woman in a blue jacket, in every scene.Redo scene 4 only. The new line is in scene-04.txt. Keep every otherscene as it is.When to use something else
For a hand that draws each picture stroke by stroke, use a whiteboard tool such as VideoScribe or Doodly. You can export from there and bring the video into invideo for voice, captions and the final cut.