Filters1 active

Wiro AI

Video Generation (1)

Image Generation

Audio & Speech

Realtime Stream

Music Generation

3D Generation

LLM & Chat

Partners

Try MiniMax H3 Image: 4K Generate + Edit from Minimaxai →
Models
Agents
Workflows
Studio
PricingBlogDocs
ExploreDiscover models by categoryDiscoverModels and effects built by WiroBrowse All ModelsBrowse the complete catalogSee FavoritesSign in to view saved models
Generative Media AgentCreate and edit media by chattingWorkflow AgentBuild visual workflows with Agent
OverviewThe platform at a glanceLearnSkills, knowledge, guardrailsAnatomyWhat makes agents reasonBuild Your AgentPick connectors and skills, choose a plan, deploy
Pre-built AgentsBrowse the catalog
Agent Usecases
Ad Campaign ManagerApp Event ManagerApp Review RepliesBarber BookingCustomer Win-BackEcommerce ListingsRestaurant Reviews
Sign InStart Building
Text to Video models

Text to video models and APIs.

Generate video clips from a prompt. Compare length, resolution, audio support and price per run across providers, then call any of them with one API.

AI Models and Tools

Showing 20 of 60 models

kling v4 flash

klingai

Kling 4.0 Flash by KlingAI generates 720p videos (3–20s) from text or a first-frame image, with aspect ratio control for text-to-video and optional watermark output.

Text to Video
Run

h3 max

MiniMax

MiniMax H3 Max generates 5–15 second videos with synced audio from text, or from first and last frame images. Pick 480P or 768P for quick iteration.

Text to Video
Run

h3 lite

MiniMax

Generate 4–15 second videos from a written prompt, with optional first and last frames to lock the opening and ending. Outputs MP4 clips at 480P or 768P.

Text to Video
Run

h3 highspeed

MiniMax

MiniMax H3 Highspeed generates 4-15s 768P videos from a prompt, with optional first and last frame images to control the opening and ending.

Text to Video
Run

kling v4

klingai

Kling V4 by KlingAI generates 5–30s videos from a written prompt or keyframe images. Create controlled motion and camera moves in 720p or 1080p.

Text to Video
Run

image-to-video-c1

PixVerse

PixVerse Image to Video C1 animates a still image into a cinematic MP4 clip, up to 1080p and 15 seconds, with optional audio.

Text to Video
Run

Fast-H3-V2

FastVideo

FastH3 V2 is an eight-step distilled MiniMax H3 that generates video with synchronized stereo audio from a text prompt, in clips of about 5 to 14 seconds at 24 FPS and 480P or 768P.

Text to Videotext-to-videoaudio-video
Run

wan 3.0 prime pro uncensored

wiro-partners

Generate 5–30 second videos from a written shot prompt, with optional first and last frame keyframes, audio on/off, and 1080p to 4K output.

Text to Video
Run

wan 3.0 prime uncensored

wiro-partners

Create 5–30s MP4 videos from a prompt, optionally anchored by first and last frame images with optional audio. Powered by Alibaba Wan 3.0 Prime.

Text to Video
Run

wan 3.0 pro uncensored

wiro-partners

Create 5–30s cinematic video from one prompt, with optional first and last frame anchors, 1080p–4K output tiers, and an audio track toggle.

Text to Video
Run

wan 3.0 uncensored

wiro-partners

Generate 5–30s MP4 videos from a prompt, with optional first and last frame images. Pick 480p–1080p resolution, aspect ratio, and audio.

Text to Video
Run

wan 3.0 prime

alibaba

Wan 3.0 Prime generates 5–30 second MP4 videos from a written prompt, with optional first and last frames. Pick 480p–1080p and an aspect ratio to shape the shot.

Text to Video
Run

wan 3.0

alibaba

Wan 3.0 by Alibaba generates cinematic videos up to 30 seconds at 1080p. Start from text alone or lock the first and last frames for tighter control.

Text to Video
Run

wan 2.6 uncensored

wiro-partners

Generate 5–15s 720p/1080p clips from a prompt, with optional first-frame image and audio. WAN 2.6 uncensored is tuned for bold motion and contrast.

Text to Video
Run

p-video-2-pro

pruna

Generate 5–15 second videos from a prompt or first and last frame images. Choose Speed or Quality, and export 480p or 768p video at 24 fps with synced audio.

Text to Video
Run

p-video-2

pruna

Generate short videos from text, a start image, or an audio track. Export 720p or 1080p MP4 with 24 or 48 fps and optional last-frame control.

Text to Video
Run

Fast-H3

FastVideo

FastH3 is FastVideo's four-step distilled MiniMax H3 (Preview v1). It generates 24 FPS video with synchronized stereo dialogue, ambience and music from a text prompt, in clips of about 5 to 14 seconds.

Text to Videotext-to-videoaudio-video
Run

seedance-2.5-uncensored

ByteDance

Create 4–30s videos from a description, or steer motion using first and last frame images. Choose 480p or 720p output with optional synced audio.

Text to Video
Run

seedance 2.5

ByteDance

Create 4–30 second videos from a prompt and optional first and last frame images, with optional synced audio. Powered by ByteDance Seedance.

Text to Video
Run

h3

MiniMax

MiniMax H3 I2V generates 4–15s videos from a prompt and optional first or last frame. It outputs MP4 video at 24 FPS with 32 kHz stereo audio.

Text to Video
Run
Showing 20 of 60 models
  • 1
  • 2
  • 3

How to pick a text to video model

Video models differ more than image models. Before comparing quality, check the clip length, the resolution, whether sound is generated, and the price, which usually depends on duration and resolution.

Strong all-rounders

Seedance 2.5 makes 4 to 30 second clips with optional synced audio, and you can steer it with first and last frames. Kling V3 and Wan 3.0 are the other two we would test first. Wan 3.0 goes up to 30 seconds at 1080p.

Video with sound

Veo 3.1 and Veo 3.1 Fast from Google generate audio along with the picture. MiniMax H3 outputs 24 fps video with stereo audio, and Grok Imagine Video adds synced audio to short clips.

Fast and cheaper

Seedance 2.0 Fast is a faster, cheaper version of Seedance 2.0 at 480p or 720p. Kling V2.5 Turbo and Pruna P-Video 2 are also built for quick turnaround, which helps while you are still tuning a prompt.

Fewer content restrictions

Seedance 2.5 Uncensored and Wan 3.0 Prime Uncensored have lighter content filtering. Both make clips of up to 30 seconds.

Frequently asked questions

How long can the videos be?

It depends on the model. Seedance 2.5 and Wan 3.0 go up to 30 seconds, MiniMax H3 up to 15. Longer clips cost more, so keep them short while you iterate.

Do these models generate sound?

Some do. Veo 3.1, Seedance 2.5, MiniMax H3 and Grok Imagine Video can return audio with the video. Others return silent clips, and you can add a soundtrack afterwards with a music generation model.

How is a video run priced?

Usually per run, with the price set by the resolution and duration you choose. For most models the page lists the price for each combination, so you know the cost before you start.

How long does a video take?

Anywhere from under a minute to several minutes, depending on the model, length and resolution. The API returns a task ID right away, and you can wait for the result over a WebSocket or have it sent to a webhook.

Discover, test, and run AI models, build workflows and agents with one unified API.

All systems operational
WiroModelsAgentsMCP ServerLLM GatewayBrowser ExtensionIntegrationsPricingAboutBlogCareersContactPartnerChangelogStatusFAQ
CategoriesText to ImageImage to ImageImage EditingImage to TextText to VideoImage to VideoVideo to VideoText to SpeechSpeech to TextSpeech to SpeechVoice CloneRealtime ConversationMusic GenerationLLMUtilities
ModelsNano Banana 2GPT Image 2.5Seedream V5 ProSeedance 2.5Veo 3.1Kling V3FLUX 3FLUX.2 ProWan 3.0 PrimeGrok Imagine 1.5
PartnersGoogleOpenAIByteDanceBlack Forest LabsKling AIQwenAlibabaxAIMiniMaxElevenLabs
Getting StartedWiro ModelsWiro EffectsIntroductionAuthenticationProjectsCode ExamplesWiro MCP ServerSelf-Hosted MCPn8n IntegrationLLMs.txt
API ReferenceModelsRun a ModelModel ParametersTasksLLM & Chat StreamingWebSocketRealtime VoiceFiles
© 2026 Wiro AI. All rights reserved.
PrivacyTermsData Deletion