Seedance 1.5 Pro

The headline change is native audio. Seedance 1.5 Pro generates dialogue, sound effects, and ambient sound together with the video and lip-syncs spoken lines, whereas Seedance 1.0 Pro outputs silent video. Seedance 1.5 Pro also adds an automatic aspect-ratio mode. Seedance 1.0 Pro remains the cheaper, silent option for visuals-only work, while 1.5 Pro is built for sound-on content.

Yes. Native audio is its defining feature. Dialogue, sound effects, and ambient sound are generated in the same pass as the video, with lip-sync for spoken lines. Audio is on by default and can be turned off if you want a silent clip. Generating with audio costs more per token than without, so silent generation is cheaper if you do not need sound.

Spoken dialogue is lip-synced so the character's mouth movements track the generated speech rather than looking dubbed. Because the audio and video are generated together rather than stitched after the fact, the timing stays tight, which is what makes the model viable for talking-character ads, spokesperson reads, and UGC-style content with on-camera speech.

It generates at 480p, 720p, and 1080p, with 720p as the default. Supported aspect ratios are 21:9, 16:9, 4:3, 1:1, 3:4, and 9:16, plus an automatic mode, so you can target ultrawide cinematic, standard landscape, square, and vertical social formats. Use 1080p for delivery and 480p or 720p for faster, cheaper iteration.

A single generation runs from 4 to 12 seconds, with 5 seconds as the default. For longer content you generate additional clips and assemble them, or step up to Seedance 2.0, which generates up to 15 seconds per clip, or Veo 3.1, which chains extensions into longer films.

On fal, a 720p five-second clip with audio costs roughly twenty-six cents. Pricing is token-based on the output dimensions, so cost scales with resolution and duration, and generating with audio costs more per token than without. Per-token and per-clip rates change over time, so check current fal pricing for exact figures. Inside Masonry, generation is metered through your workspace.

Yes. It supports image-to-video, animating a still image as the opening frame, and you can optionally supply an ending frame so the clip transitions from the start image to the end image. This makes it useful for turning product photography or brand stills into short motion clips with a synchronized soundtrack.

Yes. It is built to hold character and scene consistency as the camera moves through a shot, so a face or product stays stable rather than drifting or warping between frames. That stability is important for spokesperson content and any clip where a recognizable subject needs to look the same from the first frame to the last.

Yes, through the prompt. It responds to cinematic camera grammar including pan, tilt, zoom, dolly, orbit, tracking shots, and rack focus, and a fixed-camera toggle locks the shot to a tripod-style static frame when you want no camera movement. Describing the camera move in the prompt is the most reliable way to direct it.

Use Seedance 1.5 Pro when you want sound-on single-shot clips at a low cost and do not need 2.0's multi-shot editing or 15-second clips. It is the cheaper, simpler audio-visual option. Step up to Seedance 2.0 when a single generation needs to cut between shots or run a few seconds longer.

Seedance 1.5 Pro is intended for commercial creative work like ads, social content, and product video, and Masonry routes generation through fal under its API terms. As with any AI video model, review the current provider terms for your specific use case, particularly for regulated categories or content that depicts real people's likenesses or voices.

Describe the scene, the motion, the camera move, and the audio in one prompt, since the model generates audio natively. For dialogue, write the spoken line directly in the prompt so it can be lip-synced. Naming the ambient sound or effects you want (footsteps, room tone, music mood) produces a more complete, sound-on clip in a single pass.

Seedance 1.5 Pro is an AI video generation model from ByteDance, available inside Masonry, the AI creative agent teams use to produce marketing, product, and brand videos.

Open a Masonry canvas, pick Seedance 1.5 Pro from the model selector, and describe the video you need: a product shot, an ad creative, a social post. Masonry generates it, then you refine, edit, and combine Seedance 1.5 Pro with other models in one workspace.

Yes, you can start generating videos with Seedance 1.5 Pro on Masonry's free tier, then scale up with higher limits and priority processing as your team grows.

Write the spoken line directly in the prompt and name the ambient sound or effects you want. Seedance 1.5 Pro generates audio natively and lip-syncs dialogue, so stating the words and the soundscape gets you a finished, sound-on clip in one pass. See the prompt gallery on this page for real Seedance 1.5 Pro prompts you can copy and adapt.

Seedance 1.5 Pro is built by ByteDance. Inside Masonry it runs alongside 50+ image and video models, so your team can pick the right one for each brief without switching tools.

Yes, the prompt gallery on this page shows real videos teams have generated with Seedance 1.5 Pro in Masonry, each paired with the exact prompt you can copy and adapt for your own brand.