Generating...

Wan

1080p

16:9

Use Wan within ElevenLabs

• Generate and edit any visual imaginable
• Experience the world's best AI generation models, all within ElevenLabs

Start creating free

Trusted by 1,000,000+ creators & teams

The best image, video and audio models – all inside ElevenLabs

Generate with leading models like Nanobanana, Seedream, Kling, and Wan. Then enhance with world-class voices, music, and sound effects.

Watch Intro

Image & Video

LipSync

Upscale

ElevenMusic

AI Sound Effects

Captions

Voice Changer

Why Wan?

Wan is an advanced AI video model developed by Alibaba’s Tongyi Lab. The latest version, Wan 2.6, blends text, image, and audio inputs to produce coherent video sequences with narrative flow, character consistency, and synchronized audiovisual output — enabling richer storytelling from prompt to finished clip.

Core strengths

Multimodal input support

Generate videos from text prompts, images, video references, and audio input, building expressive scenes from hybrid sources.

Intelligent multi-shot storytelling

Automatically orchestrates narrative flow across multiple shots with consistent motion, camera angles, and transitions.

Synced audio‑visual generation

Produces video with native sync across motion, dialogue, music, and ambient sound, no manual alignment needed.

Extended video duration

Supports 5–15 second clips with scene transitions and coherent visual logic — ideal for short-form narratives and campaign assets.

Character and scene continuity

Maintains facial structure, clothing, and environments across shots for visual consistency and brand fidelity.

Add narration and sound design

Use ElevenLabs audio tools to bring Wan videos to life: voiceover with your cloned voice; original music with ElevenMusic; cinematic sound effects with AI SFX tools.

Top models, one platform

Wan runs alongside Kling, Seedream, Nanobanana, and more – all integrated into the ElevenLabs creative workspace.

Google Veo 3

Video generation
Sora 2

Video generation
Topaz Upscale

Video upscale
Veed Lipsync

Lip syncing
Nano Banana

Image generation
Flux 1

Image generation
Kling

Video generation
Seedance

Video generation
Omnihuman

Lip syncing
Wan

Image generation
Seedream

Image generation

Bring your creations to Studio — an all-in-one AI editor

Use Studio to finalize Wan projects with full control over audio, timing, and localization.

Timeline editing

Precisely control audio tracks, transitions, and effects across every second of video.

Multilingual voiceover and captions

Add expressive narration and generate captions in over 30 languages for global content delivery.

Secure sharing and collaboration

Share clips with collaborators and clients through permission-based project links.

Built for every creator

From video creators to podcasters and audiobook authors, Studio 3.0 adapts to every workflow, elevating storytelling with the polish of professional production.

Marketers and brand teams

Produce narrative ad spots and branded videos with consistent visual identity and synchronized voice.

Video creators and filmmakers

Transform prompts into multi-shot scenes with expressive audio and cinematic storytelling.

Designers and storyboard artists

Animate design frames or stills into coherent video sequences with continuity across shots.

Enterprise-grade security and infrastructure for AI Voices at scale

Enterprise-grade security and infrastructure at scale

SOC 2 Type II and ISO 27001 certified
HIPAA and GDPR compliance
EU data residency options
Zero retention for TTS and STT

Frequently asked questions

Who developed Wan?

Wan is a multimodal AI video generation model developed by Alibaba's Tongyi Lab.

What types of inputs does Wan support?

Text prompts, images, video references, and audio input, supporting rich, multi-source generation.

How long are videos generated by Wan?

Wan supports clips ranging from 5 to 15 seconds, with scene and character consistency across shots.

Does Wan generate synchronized audio?

Yes. Newer versions include native audio‑visual sync for voices, sound effects, and music.