Vidu AI 视频生成器
ShengShu Technology's video model family for native audio-video storytelling, image-to-video, and scene-oriented short-form production.
是否适合使用 Vidu?
适合用来做： native audio-video stories, short drama clips, narrative ads, multi-speaker scenes, comic and manga-style video
Skip or compare first 的情况: Vidu S1 needs a dedicated first-party profile before it is merged into the current product page. Exact API prices and regional availability are not yet normalized.
定位： ShengShu Technology's AI video family for native audio-video storytelling, reference control, and production-oriented short-form video.
核心能力
- Native audio-video outputVidu Q3 generates visuals, dialogue, voiceover, sound effects, and music together.来源
- 16-second clipsThe Q3 product page says users can generate up to 16 seconds in one generation.来源
- Q3 model variantsThe model map lists Q3 Pro, Mix, Drama, Ad, and Turbo variants for different quality and scenario needs.来源
- Multilingual outputVidu Q3 supports English, Japanese, and Chinese output according to the product page.来源
公司摘要
Built by ShengShu Technology
Founded / HQ: 2023 / China
What it does: ShengShu Technology is a general world model company whose Vidu video model line targets multimodal content generation, temporal consistency, and interactive digital-world creation.
Main products/ecosystem: Vidu, Vidu Q-series, Vidu Claw
Founders/leadership: partial/evidence pending
Scale/funding/status: Status: Venture Backed
Relationship to Vidu: ShengShu develops Vidu and related products including Vidu Q-series, Vidu Agent, Vidu Claw, Vidu API, and Vidu S1 watchlist real-time interactive generation.
价格、入口与开源状态
访问方式： Closed Web, Closed Api, Aggregator
开源/闭源： Closed.
Consumer and API pricing vary by model variant and mode. Vidu Claw introduces a result-oriented Video Plan for ads, but exact public prices need live verification.
Price, regional access, and commercial terms need a live check before cost-sensitive recommendations.
最新版本
Vidu Q3 Reference-to-Video
2026-04-13 / confirmed
Expanded reference-based generation, synchronized audio-video, visual effects, scene composition, and consistency controls. Vidu Q3 supports up to 16 seconds / synchronized audio and video generation.
最新消息
ShengShu Technology Unveils Vidu S1, Bringing Real-Time Interactive Generation to AI Video
2026-07-03 / PR 新闻wire
External source link for this model.
打开原文关键得分驱动
These are the scoring dimensions most responsible for the current ranking position.
- 模型 Quality Proxy: 89Vidu Q3 Pro is represented in Arena snapshot among top I2V systems, and official Q3 pages document native audio-video positioning.
- Capability Depth: 78Supported workflow tags: t2v, i2v, native_audio, multi_speaker, scene_cuts, industry_templates. Depth rewards T2V/I2V/V2V, references, native audio, editing, API, and open weights where pre...
- Access And Pricing: 88Access types: closed_web, closed_api, aggregator. Pricing note: Consumer and API pricing varies by model variant and generation mode. The platform model map should be paired with the curren...
- Version Maturity: 814 version/history entries in the profile; latest public date is 2026.
替代选择与对比
Use these when price, access, output style, or workflow fit is uncertain.
- KlingKuaishou's broad AI video and image generation platform for text-to-video, image-to-video, native audio, references, and creator effects.View model对比
- SeedanceByteDance's frontier video generation family for multimodal, audio-video, short-form, and cinematic creator workflows.View model对比
- VeoGoogle DeepMind's flagship video generation family for cinematic clips, image-referenced video, vertical output, native audio, and API workflows.View model对比
- PixVerseA creator-friendly AI video platform with strong API coverage for text-to-video, image-to-video, transitions, extension, and reference fusion.View model对比
它是什么
Primary content is rendered into static HTML.
Vidu is a Chinese AI video generation product from ShengShu Technology, known for Q-series releases that focus on quality, consistency, and narrative generation. The Q3 generation shifts the product toward native audio-video output and story-first use cases.
For consumers, Vidu is especially relevant when the desired output is a complete short scene rather than a silent visual clip. Q3 can generate audio, dialogue, voiceover, sound effects, and music together with the video, and it exposes variants for drama, advertising, balanced general use, and faster modes.
Vidu should be tested on dialogue timing, multi-speaker scenes, scene cuts, and promptable rhythm. It is also worth comparing against Kling, Seedance, and Veo for native audio and character consistency.
版本进展
- Vidu Q3 Reference-to-VideoExpanded reference-based generation, synchronized audio-video, visual effects, scene composition, and consistency controls. Vidu Q3 supports up to 16 seconds / synchronized audio and video generation.
- Vidu Q3 reference-to-video modelsReference-to-video adds viduq3-mix, viduq3-turbo, and viduq3 models with audio-video generation support.
- Vidu Q3Native audio-video direct output. Up to 16-second generation. Q3 Pro, Mix, Drama, Ad, and Turbo variants.
- Vidu 2.0Vidu 2.0 update announced as an earlier flagship video generation release.
- Vidu 1.x / Vidu 2.0Early public Vidu product and model generations; Vidu2.0 remains listed in the platform model map.
开源 / 来源证据
Status: Closed
Vidu model weights are not published as open weights; ShengShu references OpenClaw for Vidu Claw workflow extensibility.
最新消息
模型-specific news entries link directly to the original publisher; article bodies stay off-site.
- ShengShu Technology Unveils Vidu S1, Bringing Real-Time Interactive Generation to AI Video External source link for this model. 打开原文
- 模型 Map Official model map for Vidu Q-series variants. 打开原文
- ShengShu Technology Unveils Vidu Claw, the AI CMO That Turns a Single Brief Into a Finished Ad External source link for this model. 打开原文
- ShengShu Launches Vidu Q3 Reference-to-Video with Expanded Visual and Audio Capabilities External source link for this model. 打开原文
- Vidu API update: Q3 reference-to-video models Reference-to-video adds viduq3-mix, viduq3-turbo, and viduq3 models. 打开原文
- Artificial Analysis Text to Video Leaderboard Independent leaderboard reference for Vidu model variants. 打开原文
- Vidu Q3 AI Video 模型 with Native Audio Official Q3 consumer feature page. 打开原文
完整得分拆解
权重ed evidence dimensions separate model quality from access, web authority, ecosystem, and source confidence. See methodology and rankings.
| 维度 | Score | 权重 | 证据 | Confidence |
|---|---|---|---|---|
| 模型 Quality Proxy | 89 | 24% | Vidu Q3 Pro is represented in Arena snapshot among top I2V systems, and official Q3 pages document native audio-video positioning. | high |
| Capability Depth | 78 | 16% | Supported workflow tags: t2v, i2v, native_audio, multi_speaker, scene_cuts, industry_templates. Depth rewards T2V/I2V/V2V, references, native audio, editing, API, and open weights where present. | high |
| Access And Pricing | 88 | 12% | Access types: closed_web, closed_api, aggregator. Pricing note: Consumer and API pricing varies by model variant and generation mode. The platform model map should be paired with the current pricing page before publicat... | high |
| Version Maturity | 81 | 12% | 4 version/history entries in the profile; latest public date is 2026. | high |
| Ecosystem Popularity | 68 | 10% | GitHub stars are not applicable to this closed or research-only product unless an official public model repository is confirmed. No public source link is attached yet. |
medium |
| Web Authority | 59 | 10% | SEO snapshot found product domain vidu.com and company domain genspi.com; sampled sitemap URL count is 0. | medium |
| 公司 Distribution | 62 | 10% | ShengShu Technology distribution profile: Vidu matters for users who want a China-origin video generator with reference-to-video, sound-and-vision generation, marketing tools, and a clear roadmap from creative media int... | medium |
| 来源 Confidence | 100 | 6% | Profile source confidence is confirmed with 2 official URL(s), 4 feature evidence item(s), SEO present, GitHub n/a. | high |
限制与价格
Consumer and API pricing varies by model variant and generation mode. The platform model map should be paired with the current pricing page before publication.