Prompt-first direction
Describe a new scene without preparing source footage or a starting frame.
Create motion from a written brief
Text to Video AI Generator
Turn a prompt into a directed video
Use the Scenyra text to video AI generator to transform a written prompt into a complete moving scene. Direct the subject, action, camera, setting, pacing, lighting, and optional native audio in one workspace.
Built-in generator
Create a text to video with Seedance 2.5
Seedance 2.5 is selected by default for longer 4–30 second sequences, reference-aware continuity, and optional native audio. You can switch models before generating.
Start with the subject and action, then add camera movement, environment, lighting, pacing, and sound. Paid credits are required, and the exact total is shown before generation.
Why use this workflow
More control from the first frame to the final beat
Longer story window
Use Seedance 2.5 for 4–30 second videos or automatic timing when the idea needs room to develop.
Picture and sound together
Include dialogue, ambience, music, and effects alongside the visual direction with optional native audio.
How it works
Create with Text to Video in three steps
- 1
Write the core scene
Name the subject, the main action, and the setting. Keep the first sentence focused on what must happen.
- 2
Direct motion and camera
Add shot size, camera movement, pacing, lighting changes, atmosphere, and the intended ending beat.
- 3
Review settings and generate
Choose duration, aspect ratio, resolution, format, and audio, then confirm the exact credit total before submission.
Model choice
Start with Seedance 2.5, switch when the brief requires it
Seedance 2.5 is the default for longer 4–30 second sequences, richer continuity direction, MP4 or MOV output, and optional native audio. Seedance 2.0 remains available for 5–15 second clips and resolution options up to 4K.
Frequently asked questions
Text to Video AI Generator FAQ
What is a text to video AI generator?+
A text to video AI generator creates a moving sequence from written direction. The prompt can describe the subject, action, camera, environment, lighting, pacing, style, and sound that should appear in the result.
Which model does the text to video generator use by default?+
Scenyra selects Seedance 2.5 by default. It supports 4–30 second output or automatic timing, 480p or 720p resolution, MP4 or MOV format, and optional native audio in the current integration.
How much does text to video generation cost?+
Text to video generation uses paid Scenyra credits. The exact cost depends on the selected model, duration, and resolution and is displayed before you submit the request.
Can I switch from Seedance 2.5 to Seedance 2.0?+
Yes. Seedance 2.5 is the recommended default, while Seedance 2.0 remains available for shorter clips and output options up to 4K.