Seedance 1.5 Pro is a text-to-video model that generates short clips with synchronized audio directly from a written prompt. Most AI video tools produce silent footage, leaving you to source and mix sound separately. This model handles both at once, delivering a finished clip without the extra step. The model accepts either a text prompt or a starting image, so you can animate an existing photo or build a scene from scratch. It supports aspect ratios from ultrawide 21:9 to vertical 9:16, covering social video, cinematic widescreen, and square formats. A seed control lets you reproduce an exact clip when you need visual consistency across a series. In a typical workflow, you write a scene description, pick an aspect ratio and duration, toggle audio on, and submit. The clip comes back ready to download and drop into an editor or post directly. No additional tooling required.
Seedance 1.5 Pro is a text-to-video model that generates short video clips with synchronized audio from a single text prompt or a reference image. While most AI video tools produce silent clips that require a separate audio workflow, this model outputs a finished video where the sound is generated alongside the visuals. On Picasso IA, the whole process takes place in one step: describe what you want, choose your format, and receive a clip ready to use. That makes it practical for creators who want to produce social content, product demos, or short narratives without assembling a multi-tool pipeline.
Do I need programming skills or technical knowledge to use this? No, just open Seedance 1.5 Pro on Picasso IA, adjust the settings you want, and hit generate.
Is it free to try? Yes. You can run the model without a paid plan. Usage caps vary by account tier, but basic access is available at no cost.
How long does it take to get results? Short clips at standard settings are typically ready in under a minute. Longer durations or complex scenes can take a bit more time.
Does the model generate audio automatically? Yes. When you enable the audio option, the model creates sound that corresponds to the content in the video. There is no separate audio upload or mixing step.
What aspect ratios does it support? It handles 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, and 9:21. Note that if you provide a starting image, the aspect ratio setting is ignored and the image dimensions take precedence.
Can I reproduce a specific result? Yes. Set the seed value before generating, and reuse that same number later to get the same output. Leave it blank for a random result each time.
What if the output does not match my prompt? Rewrite the prompt with more detail about the scene, the camera angle, and specific subject behavior. More precise descriptions tend to produce closer results.
The credit cost for this model varies based on the settings you choose. Below are the costs per configuration:
Everything this model can do for you
Outputs a single video file with matching audio, skipping a separate sound editing step.
Animates a still image you provide into a short clip with natural motion.
Supports 16:9, 9:16, 1:1, 4:3, and more to fit any platform's format requirements.
Reuse the same seed to get the exact same video output across multiple runs.
Lock the camera angle to keep the scene static while subjects move within the frame.
Interprets detailed scene descriptions with multiple subjects and actions accurately.
Delivers smooth, broadcast-standard frame rate without any manual frame rate conversion.
Ideal for complex, multi-step instructions
a woman walking in the woods says: "Hello everyone! I am currently in a particularly beautiful forest, getting ready to start today's hike"
Vintage film texture. On the dim stage of a jazz bar, a rim light illuminates the side profile of a Black female singer, with beautiful bokeh in the blurred background. She closes her eyes and sings soulfully, her facial expressions brimming with rich details. She croons in a hoarse yet magnetic jazz voice, accompanied by the deep and laid-back bass in the background.
A handsome man stands atop a mist-shrouded mountain ridge. He wears sleek, practical outdoor gear — a dark charcoal windproof jacket, professional climbing pants, and a backpack over both shoulders. The mountain breeze lightly tousles his hair; his expression is calm and resolute. Behind him, surging clouds and mist swirl among jagged rocks, occasionally parting to reveal distant snow-capped peaks. The camera slowly pushes in from behind as he gazes into the abyss of rolling clouds below. In the frigid air, his breath condenses into white mist, adding natural atmospheric detail. He slightly turns toward the camera, his sharp eyes filled with unyielding determination, and says in a steady, powerful voice: “I like challenges.”
A young astronaut in a worn spacesuit sits in the dim cockpit of a spacecraft. The helmet visor is covered with fog and scratches, and the control panel flickers with orange-yellow lights, creating a tense and lonely atmosphere. The video begins with this static opening frame. The camera then rapidly zooms into the astronaut’s face before cutting to the exterior, revealing the spacecraft racing through a blizzard-like storm of cosmic debris. Sci-fi thriller style. Background music: low electronic synthesizers paired with rapidly swelling strings to build suspense. Sound effects: urgent engine hums and howling space-storm noise. Dialogue: "In the void of space, one wrong move..." followed by a brief silence, ending with: "Mayday... systems failing."
