No. Seedance 1.5 Pro is ByteDance’s December 2025 joint audio-video model. APIXO exposes its prompt and keyframe workflows separately from Seedance 2.0, Seedance 2.0 Fast, and their broader reference capabilities.
Seedance 1.5 Pro on APIXO maps to ByteDance Seed’s publicly released joint audio-video model. It creates short videos from text or one-to-two keyframes, with optional synchronized sound, 4–12 second duration control, and selectable camera behavior. The route focuses on direct generation rather than Seedance 2.0’s broader multimodal reference workflows.
Workflows
Text / Image to Video
APIXO Price
$0.0108-$0.1044 / sec
Resolution
480p / 720p/ 1080p
Duration
4–12 Seconds
Released
December 16, 2025
Loading workspace...
Generate visual motion and sound together so voices, performance timing, ambience, and spatial effects can respond to the same scene description. APIXO also permits silent output.
Coordinate lip movement, vocal intonation, action rhythm, and environmental sound more closely than a separate video-and-dubbing pipeline, while leaving room for generative timing errors.
ByteDance documents support for multiple languages and regional dialects, including their vocal prosody and emotional delivery. Pronunciation and synchronization should be reviewed for each production language.
Interpret camera and staging instructions for close-ups, continuous movement, dolly zooms, scene transitions, lighting, and color treatment within a short generated sequence.
Connect dialogue, expression, character action, and shot development around the prompt’s narrative intent, supporting more cohesive short scenes than isolated motion generation.
Animate a supplied starting image or guide a transition between defined start and end frames while retaining the source composition and appearance where generation permits.
Submit a 3–2,500 character prompt describing the scene, action, camera direction, lighting, and audio cues. Select duration, resolution, framing, sound, and camera behavior to create a new clip without image input.
Provide one public image URL as the starting frame or two URLs as ordered start and end frames. Add a required prompt to direct the motion, transition, camera treatment, and optional generated soundtrack between those visual anchors.
The production options exposed by APIXO’s current Seedance 1.5 Pro API.
3–2,500 Characters
Prompt Length
1–2 URLs
Image Inputs
Start / End
Frame Roles
6 Ratios + Auto
Aspect Ratios
On / Off
Generated Sound
On / Off
Fixed Camera
Turn a campaign brief or approved product frame into a short reveal with coordinated movement, ambience, and effects. Use fixed-camera mode for controlled compositions and inspect product shape, labels, materials, and embedded text before publication.
Create compact presenter, character, or dramatic scenes where vocal delivery, facial expression, and body movement share one prompt. Review speaker identity, pronunciation, mouth movement, hands, and emotional timing rather than treating synchronization as guaranteed.
Explore continuous takes, reframing, dolly-style movement, and transitions before committing to live-action or animation production. Start-and-end frames provide useful visual boundaries for transitions and storyboard development.
Generate 4–12 second scenes for vertical feeds, widescreen placements, teasers, or episodic concepts. Native sound can establish atmosphere and performance rhythm without requiring a separate soundtrack-generation step.
APIXO exposes text-to-video and image-to-video only; no video input, extension, editing, motion-reference, or multi-image reference mode is documented.
Image-to-video requires one or two URLs; with two images, the first is the start frame and the second is the end frame.
APIXO accepts every integer duration from 4 through 12 seconds.
The sound toggle selects jointly generated audio or silent output; it does not preserve source audio because the route accepts no source video or audio.
Typical APIXO processing ranges from roughly 40–60 seconds for a 4-second clip to 90–120 seconds for a 12-second clip; actual latency varies.
Reference images must use publicly accessible JPG, PNG, or WebP URLs and remain subject to upstream safety checks.
No. Seedance 1.5 Pro is ByteDance’s December 2025 joint audio-video model. APIXO exposes its prompt and keyframe workflows separately from Seedance 2.0, Seedance 2.0 Fast, and their broader reference capabilities.
ByteDance documents diverse voices and spatial sound effects coordinated with the visuals. Its demonstrations also include vocal performance and environmental sound, but APIXO exposes only one sound toggle rather than separate dialogue, music, ambience, or effects controls.
APIXO bills each generated second according to resolution and sound setting. At 480p, silent output costs $0.0108 per second and sound-enabled output costs $0.0216. At 720p, the rates are $0.0234 and $0.0468. At 1080p, the rates are $0.0522 and $0.1044 per second.
Yes. Supply two image URLs in image-to-video mode: the first becomes the starting frame and the second becomes the ending frame. A single image acts as the starting frame.
Check anatomy, hands, identity stability, object contact, embedded text, transitions, pronunciation, lip synchronization, and speaker interpretation. Longer or rapidly changing scenes may require prompt refinement or multiple generations.
Discover more AI models for your next creative workflow