Automatic native audio
WAN 2.5 automatically populates generated videos with relevant audio effects and speech, synchronized to the visual in one pass. That removes a separate sound-design step for social and marketing clips.
WAN 2.5 is an AI video generation model by Alibaba's Tongyi Lab that generates clips up to 10 seconds at resolutions up to 1080p, with automatic native audio synchronization and multilingual dialogue support across English, Russian, Spanish, and more.
Built for video creators, marketers, and developers, it turns briefs into fast, affordable clips with dialogue built in — backed by an open-ish license that supports self-hosted and node-based workflows through community tools like ComfyUI.
Fast affordable video generation, multilingual dialogue, product and social content
Video and marketing teams that need cost-efficient generation with automatic audio and open-ish licensing
Fast, affordable, multilingual video generation with audio built in.
WAN 2.5 automatically populates generated videos with relevant audio effects and speech, synchronized to the visual in one pass. That removes a separate sound-design step for social and marketing clips.
The model understands and generates dialogue in English, Russian, Spanish, and other languages, with what reviewers describe as a deep situational awareness of storytelling — useful for localized campaigns without a separate translation step.
WAN 2.5 offers surprisingly good prompt adherence and native audio for its cost tier, positioning it as a strong all-rounder rather than a budget compromise — even though it isn't the outright quality leader against closed frontier models.
Unlike fully closed models such as Veo and Kling, Wan's more open licensing lets teams self-host (paying for compute rather than per-clip) or build node-based pipelines through community front-ends like ComfyUI — a genuine point of difference in the category.
WAN 2.5 is positioned for faster generation and lower cost relative to rivals like Runway, Pika Labs, and early Veo releases, making it practical for teams that need volume rather than the single best frame.
WAN 2.5 fits wherever teams need fast, multilingual, cost-efficient video generation.
Add a node, describe your scene, and generate an affordable clip with audio.
Add a WAN 2.5 node to the canvas and describe your scene in a text prompt, or upload a still to animate. Set your target aspect ratio (16:9, 9:16, or 1:1) for the placement.
Set duration (5–10 seconds) and resolution. Native audio generates in the same pass. For dialogue-driven clips, write the line in the target language directly in the prompt.
Chain the node with an image model for the starting frame, an upscaler for delivery resolution, or a voice node for additional narration, then export with commercial rights on your plan.
Real generated videos with the exact prompts — copy any prompt and run it yourself.
One subscription across 30+ AI models — no per-tool credit balances or separate signups. Credit cost per generation is shown live in the node before you run it.
500 weekly credits to test the model and see the output quality. No credit card required.
45,000 monthly credits with cheaper per-credit pricing, commercial rights, and video download.
90,000 monthly credits, up to 10 seats, shared workspace, centralized billing, and priority support.
210,000 monthly credits, API and integration support, unlimited seats, and dedicated management.
Full specs for the WAN 2.5 model.
How WAN 2.5 compares with other AI video models in the Phygital+ catalog.
Chain image, video, upscaling, and audio into one repeatable workflow.
Design the first frame with an image model, then animate it with WAN 2.5 in one workflow.
Generate with WAN 2.5, then upscale to delivery resolution for social, ads, or broadcast.
Add extra narration on top of the automatic audio with a dedicated voice node.
Write the script and shot list with a text model, then feed it straight into video generation.
Everything you need to know about WAN 2.5 in Phygital+.
WAN 2.5 is Alibaba's AI video generation model from Tongyi Lab, part of the Wan open-ish video family. It generates clips up to 10 seconds at resolutions up to 1080p, with automatic native audio synchronization and multilingual dialogue support across languages including English, Russian, and Spanish.
Usage is credit-based and included in every Phygital+ plan — from the free plan up to Enterprise. The exact credit cost per generation is shown live in the node before you run it, so you can start for free and scale as you go. This is separate from Alibaba's own cloud pricing or third-party host pricing for WAN 2.5.
Outputs created on any paid plan (Starter and up) come with commercial-use rights. Note that Wan's own licensing terms vary by version and hosting method — self-hosted deployments should review the specific model license before commercial use. Check the model card for any provider-specific limits.
WAN 2.5 is made by Alibaba's Tongyi Lab. It's part of the Wan video generation family, Alibaba's flagship line in this category, which has continued to iterate through subsequent versions (Wan 2.6, Wan 2.7) after 2.5's release.
There's no single official "Wan free plan" the way some closed competitors offer a daily credit allowance, because Wan is a model rather than a single hosted product. In practice, free access comes either through self-hosting (paying only for compute) or through third-party hosts that include a small free credit allotment. Phygital+ has an ongoing free tier with 500 weekly credits for running WAN 2.5 as a node.
Clips run 5 to 10 seconds per generation at up to 1080p resolution. Some third-party hosts have extended this in beta modes, but 5–10 seconds is the standard range for the model.
Yes — automatic audio/video synchronization is one of its key differentiators, including relevant sound effects and speech populated in the same generation pass, with support for dialogue across multiple languages.
Wan carries a more open licensing model than fully closed competitors like Veo and Kling, which is why community tools like ComfyUI support Wan-based node workflows and self-hosting is possible. It's described as "open-ish" rather than fully open — check the specific license terms for your intended use.
Yes. WAN 2.5 is accessible through Alibaba Cloud's DashScope platform and through third-party API providers such as WaveSpeedAI. In Phygital+, you can run it as a node on any plan, and API and integration support is available on the Enterprise plan.
Running WAN 2.5 in Phygital+ means no separate hosting setup or API account for one model: it sits on the same canvas as 30+ other AI tools. Chain image generation, video, upscaling, and voice into one repeatable workflow under a single subscription.
Browse the full catalog of 30+ AI models available in Phygital+.
Join 100+ teams using Phygital+ – every model in one workspace
Try Phygital+ free