What video models are available?

Video generation includes OpenAI Sora 2 Pro, Sora 2, Google Veo 3.1, Veo 3, Kling 2.5, Seedance 1 Pro, and Wan 2.5. Each model offers unique capabilities for different creative needs, from photorealism to stylized animation.

What are the key capabilities?

Create high-quality videos from text descriptions or reference images. Generate dynamic video in any style, upscale to 4K resolution, add lip-sync animation, and combine with voiceovers, music, or sound effects in Studio.

What file types can I upload and download?

Video generation supports MP4 format with H.264 or H.265 encoding. You can upload reference images in PNG format and download videos up to 4K resolution.

How do I add voices and music to videos?

After generating your video, click Export to Studio. In Studio, add AI voices, lip-sync animation, music, sound effects, captions, and timeline editing for professional video production.

Can I upscale videos to 4K?

Yes. Use Topaz Upscale to boost video resolution up to 4x, delivering sharper, high-fidelity output at 4K quality. Upscaling preserves detail while enhancing clarity and visual quality.

Is video generation free?

Video generation requires a paid plan with credit-based usage. Free plans support image generation. Paid plans unlock video models, higher resolution output, and priority generation.

Write a prompt for your video...

Wan 2.5

720p

16:9

AI video generator

The best video and audio models, all inside ElevenLabs

Start Creating

Create stunning videos in seconds

Generate videos from text or images, edit in any style, and combine with professional voices, music, and sound effects to create complete cinematic content.

Video

LipSync

Upscale

ElevenMusic

AI Sound Effects

Captions

Voice Changer

Gemini Omni Flash

Massive sci-fi spaceship hovering over a vast, dense futuristic metropolis at sunset. Smaller spacecraft fly through the hazy, golden sky. Low-angle cinematic camera tracking forward.

30-second cosmic horror movie trailer, 1990s theatrical style, complete with title cards. Character A: a marine biologist in her 40s, salt-crusted parka, chapped face, deep exhaustion in her eyes. Character B: an old harbor master in his 70s, milky left eye, oilskin coat, trembling hands. Setting: a decaying fishing village on a black ocean, thick fog, crooked docks, a dead lighthouse. Structure: Cold open (0-4s): slow aerial descent through fog toward the village, the ocean unnaturally still, a vast dark shape suggested beneath the surface; low drone building. Beat one (4-9s): quick cuts, abandoned boats, nets dropped mid-haul, a meal still steaming on a crate, the biologist walking the empty dock; whispered voice-over tone. Title card (9-11s): black screen, white serif text: 'THIS SUMMER'. Beat two (11-17s): the harbor master grabs her arm and points at the water; the tide pulls back too far, too fast, exposing monolithic carved stones that should not exist; thousands of seabirds flee inland. Title card (17-19s): black screen: 'SOME THINGS SLEEP'. Beat three (19-25s): accelerating montage, the fog glowing sickly green from below, villagers running, the lighthouse flickering back to life on its own, the biologist screaming something we cannot hear, waves rising; music swelling then cutting to silence. Final card (25-28s): title reveal in weathered serif letters: 'THE DEEP BELOW', text slowly warping as if underwater. Stinger (28-30s): one last shot, the ocean surface, calm, then a colossal eye opens just beneath it; hard cut to black with a deep boom. Trailer editing grammar: rhythmic cuts synced to sound design, dread through suggestion, the creature never fully shown until the final stinger. Desaturated cold palette with sickly green undertones, heavy fog diffusion, 35mm film grain, deep sub-bass rumble, distant foghorn.

The overall mood of the video is calm and professional, with a bright and well-lit atmosphere. The setting is indoors, likely an office or corporate environment, indicated by the blurred background showing modern office furniture and glass partitions. The activity level is static, focusing on a single subject speaking directly to the camera. The visual style is realistic and modern, with a clear and crisp aesthetic. The emotional tone is informative and serious. The subject of the video is a middle-aged man with a beard, wearing a grey suit jacket and a light blue collared shirt. There are no other prominent objects or characters. The artistic style is photorealistic. The color characteristics feature cool tones with a neutral palette of blues, grays, and natural wood browns in the background.

Slow handheld tracking shot behind a detective walking down a narrow motel hallway at midnight, her wet trench coat dripping a faint trail on the carpet. She passes three numbered doors, each closer than the last. As she passes the second door, the fluorescent tube above her flickers and dies, dropping her into shadow for a beat before the next tube buzzes on. She slows, fingertips grazing the peeling wallpaper, and glances at a room-service tray abandoned on the floor, a knocked-over glass still rocking slightly. Near the end of the hall, the vending machine rattles louder and its light stutters as she passes it. In the final seconds, the last door creaks open, spilling a slice of blue TV light across the floor. She freezes, one hand slipping into her coat pocket. The shot ends holding on her still silhouette against the light. Audio: muffled footsteps on damp carpet, a fluorescent buzz that cuts out then returns, the vending machine's uneven rattle growing closer, distant rain, one sharp door creak, a TV murmuring behind a wall, no music. 1970s neo-noir, 35mm film grain, warm green fluorescent cast mixed with cold blue spill from the open door, realistic motion. No readable text, no logos, no extra people on screen.

Turn ideas into videos

Bring concepts to life with top video models. Start from text, image, or frame and create dynamic videos in seconds.

Add voices and lip-sync

Perfectly align speech and motion with Veed or OmniHuman lip-sync for natural, expressive video narration.

Layer in audio, music, and sound effects

Bring your video generations to Studio. Refine with speech, lip-sync, music, and SFX from the latest audio models to create complete cinematic projects.

Input

Output

Upscale videos

Boost clarity and resolution with video upscaling, delivering sharper, high-fidelity visuals up to 4K output.

Write a prompt for your video...

Wan 2.5

720p

16:9

Lip-sync videos

Perfectly align speech and motion using Veed or OmniHuman lip-sync for natural, expressive narration.

Add Music and SFX

Create original tracks with AI music generation and enhance with cinematic sound effects for professional depth.

Voice cloning

Clone your voice to produce lifelike, expressive narration powered by your own unique vocal character.

Multilingual voices

Choose from 5,000+ voices in 32+ languages to add narration that fits any story, style, or audience.

Bring your creations to Studio

From captions and collaboration to video support and multi-language audio, Studio 3.0 gives you everything you need to create and share at scale.

Timeline

Line up voiceovers, music, and effects with precision. Edit every element in sync - all in a single, intuitive timeline.

Audio and Video support

Upload your video files and enhance them with AI-powered voiceovers, music, sound effects, and captions.

Captions

Generate captions in one click to boost accessibility, reach, and engagement - with customizable styles to match your content.

Public project URLs

Share drafts with teammates or clients via a simple link - collect time-stamped feedback directly on the timeline.

32+ Language support

Create in over 30 languages with natural voices, expressive accents, and localized audio tailored to your audience.

Built for every creator

From video creators to filmmakers and marketers, video generation adapts to every workflow, elevating visual storytelling with cinematic quality.

Image & Video Pricing

$0 per month

10k credits per month

Free

$0 per month

Build for free

Starter

$6 per month

Choose Starter

Creator

$22 per month, first month $11

Choose Creator

Pro

$99 per month

Choose Pro

10k credits per month

30k credits per month

121k credits per month

600k credits per month

Images included

Videos included

Upscaling

Lipsync

Daily generation limit

Up to 40 images

3

Up to 198 images

Up to 211 seconds

198 images, 49 seconds of video

742 seconds

Unlimited

Up to 660 images

Up to 705 seconds

660 images, 165 seconds of video

2,475 seconds

Unlimited

Up to 3,300 images

Up to 3,525 seconds

3,300 images, 825 seconds of video

12,375 seconds

Unlimited

Prices exclude all taxes, levies and duties. View all pricing plans.

AI video generator

Create stunning videos in seconds

Gemini Omni Flash

Gemini Omni Flash

Turn ideas into videos

Add voices and lip-sync

Top video models in one place

Layer in audio, music, and sound effects

Upscale videos

Lip-sync videos

Add Music and SFX

Voice cloning

Multilingual voices

Bring your creations to Studio

Timeline

Audio and Video support

Captions

Public project URLs

32+ Language support

Built for every creator

AI kissing generator for romantic videos

Remove text from video easily

Lip sync AI for dynamic video creation

AI dance video creation

Animated wallpaper maker

AI talking avatar generator

AI talking photo generator

AI GIF generator

AI cartoon video generator

Image & Video Pricing

Enterprise-grade security and infrastructure at scale

Enterprise-level data protection

Granular team permissions

Elevated support and custom deployments

Frequently asked questions