# Wan 2.7 > Wan 2.7 is available on Artifio.ai — a unified AI workspace with a single pay-as-you-go wallet. - Canonical page: https://artifio.ai/models/wan-2-7-text-to-video - Run it: https://artifio.ai/create/wan-2-7-text-to-video - Modality: prompt to video - Model brand: Wan - Pricing: from about $0.080 per second (exact cost shown in the workspace before you confirm; varies with selected options) - Typical generation time: ~300s (catalogue estimate) - Full pricing table: https://artifio.ai/pricing/models ## About Wan 2.7 Wan 2.7 is the April 2026 generation of Alibaba's Wan video family. The Wan2.7-Video release comprises four models, and the text-to-video model (Wan2.7-t2v) is its front door: a text prompt in, a multi-shot 720p or 1080p clip out, with dialogue, sound effects, and lip movement generated together. Alibaba pitched the release as moving creators from executors to directors, leaning on natural-language control over shots, styles, and camera work. The generation has held up in third-party testing: as of July 2026 the Artificial Analysis text-to-video arena places Wan 2.7 at an Elo of 1102, and a June 2026 checkpoint (Wan2.7-260612) second overall at 1160. Artifio offers it in one workspace with 100+ other models, billed per generation. ## Features - 720p or 1080p output at 30 fps with synchronized audio generated in the same pass. - Any integer duration from 2 to 15 seconds. - Builds multi-shot storyboards from a single prompt, including drone perspectives and 360-degree shots. - Voice output spans thousands of style combinations and more than 50 refined emotional expressions. - Dozens of basic and complex camera movements can be specified while lighting stays consistent. - Cross-video consistency for up to five distinct characters, each with an exclusive voice tone and visual identity. ## What people use it for - Short ads and brand films with spoken dialogue delivered in one generation. - Multi-shot narrative previsualization from a written treatment. - Serialized short-form content that reuses a consistent cast of up to five characters. - Cinematic mood pieces where camera language matters as much as subject. ## Reported strengths - Ranked near the top of the Artificial Analysis text-to-video arena as of July 2026, with the June checkpoint second only to Seedance 2.0. - Audio, lip sync, and emotional voice delivery are native rather than post-processed. - Character and voice consistency across separate videos supports campaign-length storytelling. - Flexible 2-to-15-second durations rather than a fixed menu. ## Reported limitations - Video output tops out at 1080p and 15 seconds; there is no 4K or long-form option. - Even the June 2026 checkpoint trails Seedance 2.0 on the arena (Elo 1160 versus 1226). - Wan 2.7 ships as a hosted service only; the newest open-weight release in the Wan GitHub line remains Wan 2.2. ## Sources 1. Alibaba unveils Wan2.7-Video to elevate creators from executors to directors (Alibaba Cloud): https://www.alibabacloud.com/blog/alibaba-unveils-wan2-7-video-to-elevate-creators-from-executors-to-directors_603009 2. Video generation, Alibaba Cloud Model Studio documentation (Alibaba Cloud): https://www.alibabacloud.com/help/en/model-studio/use-video-generation 3. Alibaba releases Wan2.7-Video AI model for multimodal video generation and editing (The Elec): https://www.thelec.net/news/articleView.html?idxno=6445 4. Text to video leaderboard (Artificial Analysis): https://artificialanalysis.ai/video/leaderboard/text-to-video 5. Wan2.2: open and advanced large-scale video generative models (GitHub (Wan-Video)): https://github.com/Wan-Video/Wan2.2 ## What it's good at - Big-energy scenes are its sweet spot: our wave test delivered the most explosive, dramatic spray of the battery with strong rock texture and heavy golden atmosphere. - Flexible duration range (2-15 seconds) gives it the widest native clip-length envelope among the video models we tested. - Solid value for 1080p work relative to the premium tier — it defaults to 1080p where most rivals default to 720p. ## Where it falls down - Fine particle detail is its weak point: dense spray renders slightly 'cottony' rather than droplet-crisp, softening close inspection. - The slowest model in our video battery — 275 seconds for a 5-second clip, roughly 4x Veo Fast on the same prompt. - Real per-clip cost at 5s/720p charged 5x the catalogue's base price line — verify the live per-config price before committing to a batch. ## Best for - High-energy nature and action shots - Longer clips (up to 15s) - 1080p-first workflows ## Sample generations (exact prompts) All samples below were generated on Artifio.ai with this model and are hosted on our media CDN. ### The most explosive spray of our battery; note the dense texture Prompt: "A large ocean wave crashing over dark rocks at golden hour, slow motion, spray and droplets backlit by the sun" Output (video): https://media.artifio.ai/users/user_3Bm1K1h3HGUm1KEaek1PCLVody6/outputs/wan-2-7-text-to-video/2026/07/12/1783817877327-9ee8de33-e4fd-4535-984c-e586f7ec2727.mp4 ### Correct steel pitcher and clean pour at close range Prompt: "A barista pours latte art into a white cup in a bright café, camera slowly pushes in on the cup, steam rising" Output (video): https://media.artifio.ai/users/user_3Bm1K1h3HGUm1KEaek1PCLVody6/outputs/wan-2-7-text-to-video/2026/07/12/1783818160699-82a85ea9-40cd-4157-803a-063d97d8a916.mp4 _Strengths and weaknesses above were observed in real generations by the Artifio team, not taken from vendor marketing copy._ --- About Artifio.ai: 100+ AI image, video, and audio models in one workspace with a single shared wallet — no per-model subscriptions. This is the markdown rendition of https://artifio.ai/models/wan-2-7-text-to-video for AI assistants and crawlers; the HTML page is canonical.