Words only
Start from a sentence, with nothing to prepare.
Nano Banana 2.1 is live — sharper edits, cleaner text, up to 4K
Text to Video AI
Write the shot — subject, action, camera move, mood — and watch it render with synchronized sound.
AI Model 5 credits
Prompt0/2000
Avoid copyrighted characters, logos, music and sensitive or explicit content — it may be blocked.
Resolution
Aspect Ratio
Batch generation1
Estimated cost: 5 credits
Your creation appears here
Pick a model, describe the shot, and hit Generate.
Why Text to Video AI
Why creators choose Text to Video AI
Describe the shot, pick a model, and get a clip. No uploads and no editing software.
Camera control
Camera terms in the prompt shape the shot.
Optional sound
Use Muse Video or Seedance to generate audio with the picture.
Model choice
Run the same prompt on several engines.
Text to video guide
How to turn text into video
Text to video lets you describe a shot in words and receive a moving clip. This page covers how to write prompts that a video model can follow, and which model to start with. You do not need to upload anything.
How text to video works
You write a prompt, choose a model, resolution, aspect ratio, and duration, and the model renders motion that matches the description. Muse Video is the default, since it handles a wide range of prompts and can generate sound. Veo 3.1, Wan 3.0, Kling 3.0, MiniMax H3, and the Seedance models are also available in the same panel.
Writing prompts that work
A reliable video prompt has four parts: subject, action, camera, and light. "A lighthouse keeper climbs a spiral staircase, handheld follow shot from below, warm lantern light" is specific and short. Add one camera term, such as push-in, orbit, tracking, or static wide.
Describe one action per clip. If you want a sequence, generate the beats as separate clips, or list them in order in a single sentence. Avoid contradictory instructions, such as "fast zoom" together with "static shot".
Subject and action
Who or what is on screen and what they do.
Camera language
Push-in, orbit, tracking, handheld, or static.
Light and mood
Golden hour, neon night, overcast, or studio.
Choosing settings
Use 480p and a short duration for tests. Choose 16:9 for widescreen, 9:16 for vertical feeds, and 1:1 for square posts. If the first result is close, change one thing in the prompt and run again rather than starting over.
How to use Text to Video AI
How to use Text to Video AI in three steps
Subject, action, camera, and light in one or two sentences.
00:0000:1500:30
Who uses Text to Video AI
Who uses Text to Video AI for image work
Concept artists
Moving mood boards from a paragraph of text.
Social teams
Quick clips for trending formats.
Founders
Promo footage without a production crew.
Writers
See scenes from a script or story.
More models
Text to Video AI and every other model in one studio
Switch engines without switching tools — Nano Banana 2.1 plus the strongest public image and video models, side by side in the Nano Banana AI studio.
Multi-reference editingCharacter consistencyText rendering1K–4K outputConversational editsStyle transferVideo generationBatch runs
Muse VideoNewFlagship multimodal video with native audio
Seedance 2.5HotMulti-reference Seedance with native audioSeedance 2.0Previous-gen Seedance up to 4KSeedance 2.0 FastFastFastest Seedance tier for drafts
MiniMax H3Fast text/image to video up to 2KMiniMax H3 MaxHotReference-driven video consistency
Veo 3.1Google’s cinematic drafting engine
Wan 3.0Flexible duration and adaptive framing
Kling 3.0Dramatic motion from a single prompt
GPT Image 2.5NewSharp text and precise edits to 4KGPT Image 2Versatile image generation to 4KNano Banana 2.1NewFast drafts and precise edits to 4KNano Banana ProHotHigh-fidelity image output to 4KNano Banana 2Fast drafts and conversational editsNano Banana 2 LiteFastLightweight tier for quick, low-cost draftsFAQ
Text to Video AI FAQ
How do I write a good video prompt?
Lead with the subject and action, then add camera language ("slow push-in", "aerial orbit") and lighting mood. Our prompt guide has templates.
How long can a text-to-video clip be?
Seedance 2.5 generates up to 30 seconds per run; most models sit in the 4–15 second range.
Can I generate without a prompt?
Reference mode lets stills drive the generation, but a short prompt always improves control.
Which model should I start with?
Muse Video — it handles the widest prompt range and adds native audio.