Vidu AI Video Generator: Try Vidu Q3 Online, with Sound
Make Vidu AI videos in your browser with Vidu Q3, ShengShu’s video model with native audio. Type a prompt or add an image and get a clip of up to 15 seconds at up to 1080p, with dialogue, sound effects and music made together with the picture. No Vidu account, no app, nothing to install.
- No app, no install
- Up to 15s per clip
- Up to 1080p with sound
- Text or image to video
Sexually explicit (NSFW) content is strictly prohibited.
Vidu Q3 examples
Clips made with Vidu Q3, sound included. Hover to play and turn the sound on. Where the prompt was published, open it or put it in the box and make your own version.
Wide clips, from 4 to 15 seconds
Each one is a single generation — the cuts in some of them are Vidu’s own.
15 seconds in one generation
A warrior kneels in the rain over a glowing sword, then rises — slow, moody and scored, without a cut stitched in afterwards.
Several shots, one clip
A summer look in quick cuts: close-up under a straw hat, then wide on the beach, cut to the beat of the music.
Lifestyle ad with ambience
A woman in a trench coat smiles into the wind and rides off down an old town street, with natural street sound.
Astronaut in the fog
A one-line prompt in a fashion-photo look: pale blue and amber tones, slow steps through mist.
Show the prompt
In an ultra-realistic fashion photography style featuring light blue and pale amber tones, an astronaut in a spacesuit walks through the fog.
FPV through a mushroom forest
A drone shot with a barrel roll between glowing mushrooms, with wind and chimes asked for in the prompt.
Show the prompt
Fast-paced FPV drone shot flying through a miniature magical mushroom forest. The camera weaves rapidly between giant glowing mushrooms and mossy rocks. Cinematic motion blur. The camera performs a barrel roll while flying through a narrow gap between two mushroom stems. Dynamic lighting changes as the camera moves from shadow to light. Sound of wind rushing and magical chimes.
Cuts inside one prompt
Hacker, security team, hacker again: the prompt asks for two cuts and the clip makes them.
Show the prompt
A suspenseful sequence showing a hacker working intensely at a terminal, followed by a sudden cut to a wide shot of a security team rushing down a hallway, then cutting back to the hacker’s focused eyes.
Anime village at dawn
A painterly anime town waking up, with smoke rising from the chimneys.
Fantasy party on the road
A knight, a mage and an archer walk through an enchanted forest, drawn like a TV anime.
Floating city
Airships drift past waterfalls pouring off a city in the clouds at sunset.
Vertical anime clips
Generated at 9:16, not cropped from a wide frame.
Samurai under cherry blossoms
A glowing blade raised in a storm of petals, framed for the feed.
Potion brewing
A hand stirs a bubbling green cauldron by candlelight in a witch’s study.
Cat and pancake
A chibi kitten balances a pancake on its head in a pastel café.
Rainy street, anime style
A schoolgirl with a rainbow umbrella walks past shop windows on a wet night.
What is Vidu AI, and what is Vidu Q3?
Vidu AI is a family of video generation models from ShengShu Technology, a Beijing company with roots in Tsinghua University. ShengShu runs Vidu in its own app at vidu.com and sells it to developers through an API; the models have gone from Vidu 1.5 and 2.0 to the Q series — Q1, Q2, Q3 and, most recently, Q4.
Vidu Q3 is the version that brought sound into the model: dialogue, narration, sound effects and music are generated together with the picture, characters can talk to each other, and one clip can cut between shots on its own. Speech works in English, Chinese and Japanese.
ToonBee AI runs Vidu Q3 and Vidu Q3 Turbo through fal, so this is an unofficial way to use Vidu AI: not ShengShu’s own service, and no Vidu account needed. Here you can start from text, an image, or a first and a last frame on both, and from up to 4 reference images on Vidu Q3, at 540p, 720p or 1080p and 4–15 seconds. Vidu Q4, the Vidu app’s effect templates and voice references are not offered here.
How to use Vidu AI online
- 1
Write a prompt or add an image
Describe the scene, the action, the camera and the sound, and put anything a character says in quotes. Add an image to start from it, or set a first and a last frame.
- 2
Pick the model, size and length
The box starts on Vidu Q3 Turbo at 540p and the shortest length, the cheapest clip. Switch to Vidu Q3 for reference images, choose 540p, 720p or 1080p, and watch the credit cost update as you go.
- 3
Generate and download
Press Generate video. The clip lands in your history with its sound and downloads as an MP4 with no watermark.
Vidu Q3 vs the other video models here
Vidu next to the other video models you can pick on ToonBee AI, read from the generator’s own tables. Credits are for a 5-second clip, from the smallest size to the largest.
| Model | Max size | Length | Native audio | Image to video | First + last frame | Reference images | Credits (5s) |
|---|---|---|---|---|---|---|---|
| Vidu Q3 | 1080p | 4–15s | 175–385 | ||||
| Vidu Q3 Turbo | 1080p | 4–15s | 88–193 | ||||
| Wan 3.0 | 1080p | 4–30s | 125–500 | ||||
| Seedance 2.5 | 1080p | 5–30s | 238–1,328 | ||||
| H3 Max Turbo | 1080p | 5–15s | 63–200 |
Vidu Q3 Turbo is the same model as Vidu Q3, run faster at half the credits; Vidu Q3 is the one that takes reference images. Of the models in this table, Vidu Q3 Turbo makes a 1080p clip with sound for the fewest credits.
Vidu Q3 vs Q3 Turbo
Same model, same sizes and lengths. Turbo renders in about a minute at half the price; Q3 takes longer, costs twice as much and is the one that reads reference images.
Vidu Q3 vs Vidu Q2
Q2 makes clips of up to 8 seconds with, at most, background music. Q3 generates dialogue and sound effects with the picture, runs to 16 seconds upstream, and cuts between shots inside one generation. ToonBee AI runs Q3 only.
Vidu Q3 vs Wan 3.0
Both make video with its own sound. Wan 3.0 runs to 30 seconds in one take; Vidu Q3 stops at 15 here but costs fewer credits per clip at 1080p. Try one prompt on each from the same box.
Vidu Q3 vs Vidu Q4
Q4 is ShengShu’s newest model, with up to 4K and more reference images. It is not offered here yet; this page runs Q3.
Why use Vidu AI here
Sound in the same pass
Dialogue, sound effects and music are generated with the picture. Put a line in quotes and the character says it.
Up to 15 seconds a clip
Long enough for a whole moment, and Vidu can cut between shots inside one clip when the prompt asks for it.
Up to 1080p
Pick 540p for a cheap first try, then 720p or 1080p for the keeper.
Text, image, frames or references
Start from a prompt, animate an image, pin a first and a last frame, or add up to 4 reference images on Vidu Q3 to keep a character or product consistent.
No Vidu account, no app
No download, no API key, no GPU. It runs in any modern browser on a laptop, a PC or a phone.
The price before you press
The box shows the credit cost before you generate, and if a generation fails its credits come back automatically.
What people make with Vidu AI
Anime and comic-style scenes
Characters, villages and fantasy worlds in an anime look, with sound, for shorts and comic dramas.
Short drama moments
Two characters talking, a reveal, a cut to a reaction — inside one clip.
Ads and product shots
A lifestyle moment or a product close-up with ambience and music, without a shoot.
Images brought to life
Start from a picture you made with an image model, or a photo, and set it in motion.
Vertical clips for the feed
Native 9:16 for TikTok, Reels and Shorts, generated upright rather than cropped.
Camera moves
FPV flights, push-ins and orbits written into the prompt and followed by the model.
Need a whole story with narration? Try the story video generator
Is Vidu AI free? What does a clip cost?
Vidu’s own app gives new users some free credits and sells plans after that; through the API it is billed by the second. There is no open-source Vidu model to run on your own GPU.
On ToonBee AI the account is free and generating uses credits, priced per clip; the box shows the cost before you press. A 5-second Vidu Q3 Turbo clip is 88 credits at 540p and 193 at 1080p. On Vidu Q3 it is 175 at 540p and 385 at 720p or 1080p; a full 15-second Vidu Q3 clip at 1080p is 1,155.
Plans start at $39 a month for 5,000 credits. Prefer not to subscribe? A one-time pack is $49 for 4,000 credits that never expire. Every plan covers commercial use and downloads with no watermark.
Good to know before you start
- One clip runs 4–15 seconds. For something longer, ToonBee 1.0 makes an edited video from 15 seconds, and the story video generator builds narrated videos of several minutes.
- Vidu reads the first 2,000 characters of a prompt; anything past that is left out. Keep long scripts tight.
- Vidu runs with a content filter that turns away some prompts and images — now and then harmless ones too. A refused generation gives its credits back.
- Not offered here: Vidu Q4, the Vidu app’s effect templates, voice references, 2K and 4K, and video extension.
- Reference images work on Vidu Q3, not on Q3 Turbo.
Vidu AI FAQ
What is Vidu AI?
Vidu AI is a family of AI video generation models from ShengShu Technology, a Beijing company with roots in Tsinghua University. It turns text and images into video clips; ShengShu runs it in its own app at vidu.com and through an API.
What is Vidu Q3?
Vidu Q3 is the Vidu model that generates sound with the picture: dialogue, narration, sound effects and music in one pass, with characters that can talk to each other and cuts between shots inside one clip. It is the version this page runs, alongside its faster Q3 Turbo.
Is Vidu AI free?
On ToonBee AI the account is free, but generating uses paid credits: the shortest clip, 4 seconds at 540p on Vidu Q3 Turbo, is 70 credits, and credit packs start at $49. Vidu’s own app has its own free credits and plans.
How much does a Vidu Q3 video cost?
Here a 5-second clip is 88 credits at 540p on Vidu Q3 Turbo, or 175 on Vidu Q3; at 1080p it is 193 and 385. The cost scales with length. Plans start at $39 a month for 5,000 credits.
How long can a Vidu video be, and what resolution?
Each clip is 4–15 seconds, at 540p, 720p or 1080p, in 16:9, 4:3, 1:1, 3:4 or 9:16.
Does Vidu Q3 generate audio?
Yes. Dialogue, sound effects and music come out with the picture. Write a line in quotes and the character says it; English, Chinese and Japanese speech work.
Can Vidu AI turn an image into a video?
Yes. Add an image and the clip starts from it; add a second one to set the last frame too. On Vidu Q3 you can instead add up to 4 reference images for a character, product or place.
Vidu Q3 or Q3 Turbo: which should I pick?
Turbo is the same model at half the credits and about twice the speed, so it is the one to try a prompt on. Pick Q3 when you want reference images, or to compare the two on a keeper.
Is Vidu Q4 available here?
Not yet. Vidu Q4 is ShengShu’s newest model; this page runs Vidu Q3 and Q3 Turbo.
Why was my Vidu prompt refused?
Vidu runs with a content filter on prompts and images, and it can be strict. Rephrase the prompt or try another image. A refused generation gives its credits back.
Is this the official Vidu AI site?
No. ToonBee AI is an independent video generator, not affiliated with ShengShu Technology. It runs Vidu Q3 through fal. ShengShu’s own Vidu app is at vidu.com.
Can I use Vidu AI videos commercially?
Yes. Videos you make on ToonBee AI can be used commercially, and they download with no watermark.
Make your first Vidu AI video
Type a prompt or add an image. No app, no install, and the price shows before you generate.
Make a Vidu AI videoRelated tools
Other pages that open the same studio, set up for a different kind of video.
- Kling AI Video GeneratorKling 3.0 clips up to 15 seconds, in 1080p with sound.
- PixVerse AI Video GeneratorPixVerse V6 and C1 clips up to 15 seconds, in 1080p with sound.
- MiniMax H3 Video GeneratorMiniMax H3 videos with sound, on H3 Max in your browser.
- Wan AI Video GeneratorWan 3.0 videos up to 30 seconds, in 1080p with sound.
- Dola AI Video GeneratorDola-style Seedance videos online, with no watermark.
- AI ModelsEvery video and image model, with lengths and prices.
- AI Anime Video GeneratorStory videos drawn in an anime style, with narration.
ToonBee AI is an independent video generator. It runs ShengShu’s Vidu Q3 through fal. It is not the official Vidu site (vidu.com) and is not affiliated with or endorsed by ShengShu Technology. Vidu is a trademark of its owner.