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

Bring your videos to life

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

Google Veo 3

The video features an abstract, static composition of geometric blocks and shapes, creating a sense of calm and precision. The setting is a minimalist indoor environment with a plain, neutral background. The visual style is modern and artistic, utilizing 3D rendering to create a realistic yet stylized aesthetic. The emotional tone is neutral and contemplative, focusing on form and color. The subject is a tower constructed from various block shapes including cubes, cylinders, and spheres, predominantly in shades of red, orange, and pink. The artistic style leans towards 3D computer graphics with a photorealistic rendering of textures and shadows. The color characteristics include warm tones with high saturation, creating a vibrant and engaging palette of reds, oranges, and a striking magenta-pink.

This video presents a dark and mysterious atmosphere, set in an indoor, possibly underground, ancient ruin. The activity level is static, focusing on a single, imposing object. The visual style is realistic, with a dramatic and somber emotional tone. The main subject is an elaborate, broken stone throne, adorned with golden, intricate patterns, suggesting a lost civilization or fallen power. The artistic style leans towards photorealism with fantasy elements, reminiscent of video game cinematics. The color characteristics are predominantly cool tones with warm, glowing accents from embers or dust, creating a high contrast and dramatic effect. The overall color palette is dark grey, black, and muted gold, with subtle orange highlights.

The overall mood of the video is dark and mysterious, with a calm atmosphere focused on a singular action. The setting appears to be indoors, likely a sound recording studio, indicated by the sound-dampening foam panels visible. The activity level is static, focusing on a close-up of a person's mouth. The visual style is realistic, with a focus on details of the lips and skin. The emotional tone is neutral, perhaps hinting at concentration or performance. The subject of the video is a person, specifically their lower face, featuring prominent dark red lipstick. The artistic style is photorealistic, utilizing chiaroscuro lighting to create dramatic shadows and highlights. The color characteristics include cool tones and low saturation, with the deep red lipstick providing a strong accent against the dark background. The color palette is dominated by dark grays and blacks, accented by the rich, dark red of the lips.

This video presents a dramatic and mysterious scene within a dark cave setting. A group of five macaque monkeys, with realistic fur textures, are gathered around a central, glowing blue-green crystal or stone. The overall mood is serious and contemplative, with a hint of wonder. The primary subject is a larger monkey in the center, looking up and pointing with its right hand, seemingly addressing or guiding the younger monkeys surrounding it. The movement is static, focusing on the expressions and interaction of the monkeys. The visual style is highly realistic, almost photorealistic, with a dramatic use of lighting. The emotional tone is one of curiosity, intrigue, and possibly a sense of discovery. The color characteristics are dominated by cool tones, particularly blues and greens from the glowing object and surrounding cave, contrasted with the earthy brown and grey tones of the monkeys' fur. The color palette is dark blue, green, and brown with bright cyan highlights.

This animated video features a bright, calm, and slightly dramatic mood. The setting is a traditional Japanese indoor space, looking out onto a vast outdoor natural landscape. The activity level is static, focusing on a single moment. The visual style is artistic and realistic, reminiscent of Makoto Shinkai's work. The emotional tone is peaceful yet awe-inspiring, as a lone girl observes an approaching storm. The main subject is a young girl with dark hair, wearing a white dress, standing in a green field. A massive, beautiful storm cloud dominates the sky. The artistic style is detailed anime, with photorealistic elements. The color characteristics are bright and vibrant, with a high saturation, featuring a palette of blues, greens, and whites.

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.

Bring your videos to life

Create stunning videos in seconds

Google Veo 3

Google Veo 3

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

Remove text from video

AI dance

Animated wallpaper maker

Convert videos to photos

AI cartoon video generator

Sound wave maker

AI movie trailer maker

Enterprise-grade security and infrastructure at scale

Enterprise-level data protection

Granular team permissions

Elevated support and custom deployments

Frequently asked questions

What video models are available?

What are the key capabilities?

What file types can I upload and download?

How do I add voices and music to videos?

Can I upscale videos to 4K?

Is video generation free?