ViggleWrite the prompt
Describe one shot: who is on screen, what they do, where it happens, how it is lit, and how the camera moves. Nothing has to be uploaded first - the prompt is the whole input.
Text to video
Viggle AI Text to Video: From Prompt to Clip
No footage, no image, no timeline: one written prompt becomes a four to eight second character clip in HD or 720P.
No Upload Needed4 to 8 Second ClipsHD or 720PPrompt Only WorkflowPlans From $9/Month
Text to video is the fastest route through the generator, and the one that asks the most of your writing. There is nothing to upload and nothing to attach, so the prompt alone decides the subject, the movement, the setting, the light, and the camera.
It is also the workflow people misjudge: the same prompt that disappoints as a finished shot usually works well as a test of an idea. The sections below cover what the workflow does, what it costs, and when a different route produces a better clip.
Generating a clip from text alone
Four steps, no uploads, and the credit estimate is shown before the run.
Choose duration and resolution
Pick a length between 4 and 8 seconds and choose HD or 720P. The credit estimate for the run appears before you confirm, so the cost is known up front.
Generate the clip
Run the generation and watch the take. The model builds the subject, setting, and movement from your description, so there is no footage to prepare and no timeline to edit.
Refine one thing at a time
If the clip is close, keep the prompt and change one slot - the action, the light, or the camera. Regenerating with a single edit tells you what actually changed the result.
Prompt-only input, references stay optional4 to 8 seconds per generationHD or 720P outputWatermark-free download
The five-part prompt formula
A prompt that produces a usable clip answers five questions in order: who is on screen, what they do, where the shot happens, how it is lit, and how the camera behaves. Missing answers are not left blank - the model fills them with defaults, which is why a subject-only prompt produces a generic shot.
Twenty to forty words is usually the sweet spot. That is long enough to cover all five slots and short enough that no instruction gets diluted, and it keeps the whole prompt inside the four to eight seconds the clip actually has.
Subject - the uploaded character or a described person, mascot, or objectAction - one movement, not a sequence of threeSetting - where the shot happens, which also sets the colourLight - one direction, one qualityCamera - framing plus a single move, such as a slow push in
Duration, resolution, and output
Three settings decide what you get back, and only one of them changes the price you can see before the run.
| Setting | Options | What it changes |
|---|---|---|
| Duration | 4 to 8 seconds | How much of the described action fits in one shot |
| Resolution | HD or 720P | Output detail, and how many credits the run costs |
| References | Optional | Not needed for text to video; add them only to pin down a subject |
| Output | Watermark-free download | The finished clip, ready to drop into an edit |
Text to video versus the other workflows
The three workflows share one generator. Which one you pick depends on what you already have in hand.
| Workflow | What you provide | Best for |
|---|---|---|
| Text to Video | A written prompt only | Exploring a scene before committing to production |
| Image to Video | A character image plus a prompt | Keeping a specific character consistent across shots |
| Motion Transfer | A character image and a short motion clip | Reusing a real performance, dance, or gesture |
What a text to video run costs
Credit cost follows the output, not the input: length and resolution decide the price, and a prompt costs nothing to write. A six second HD clip is roughly 45 credits, 720P and shorter clips cost less, and the estimate appears in the generator before you confirm the run.
Monthly plans start at $9 for 100 credits, which is around two six second HD attempts, and every plan renews its credit allowance at the start of each billing period. Annual billing costs the same as ten months.
When text to video is the wrong choice
Text to video is at its best when the idea is still open: testing a scene, a mood, or a camera move before any material exists. It is at its weakest when the brief is about fidelity - matching a client face, reproducing a dance, or keeping one character identical across a series of shots.
For a specific character, start from an image instead and let the prompt handle the action and camera. For a specific performance, attach a short motion clip and describe only the setting, light, and camera around it. Both routes use the same credits and the same generator.
The subject has to be a specific face or characterThe movement has to match a real performance exactlySeveral clips have to share one consistent characterThe shot depends on footage that already exists
Continue with the image to video guide for character consistency, or the Viggle AI prompts guide for templates you can paste into a text-only run. The Viggle AI free guide explains what the site offers before a plan is needed.
Viggle AI Text to Video: From Prompt to Clip FAQ
What is Viggle AI text to video?+
It is the workflow that turns a written prompt into a short character clip, with no image, video, or audio uploaded first. The prompt carries the subject, the action, the setting, the light, and the camera, and the model builds the shot from that description.
Do I need to upload a character for text to video?+
No. Uploads exist to pin down a specific character, performance, or voice; they are not a requirement. If a shot has to match a real subject, use image to video instead so the character stays consistent across takes.
How long can a text to video clip be?+
Between four and eight seconds. That window is long enough for a turn, a walk, or a camera move, and short enough that the subject does not drift. Longer sequences are normally assembled from several short generations rather than requested in one prompt.
How much does a text to video generation cost?+
Less than a full-scale production and less than most people expect: a six second HD generation is roughly 45 credits, and shorter or 720P clips cost less. The exact estimate is shown in the generator before you confirm, and a generation that fails and returns no output is not charged.
What can text to video not do?+
It cannot reproduce one exact face or one exact performance, because there is no reference telling the model which face or which movement to keep. It also cannot hold a specific camera path across several clips on its own; for consistency across shots, start from a character image instead.
Does the prompt need special syntax?+
No syntax is required, but typing @ opens a picker if you want to attach a character, motion clip, or audio track inside the prompt. A text-only run simply skips that step, and the five-part formula - subject, action, setting, light, camera - is the only structure worth following.
Turn one prompt into a clip
Sign in with Google, describe a single shot, and render a four to eight second character video in up to HD.