The route accepts text-to-video, image-to-video, turbo-text-to-video, and turbo-image-to-video. It does not expose Q3 Mix, Drama, Ad, reference-to-video, extension, editing, video transfer, action synchronization, or subject-library workflows.
Vidu Q3 on APIXO provides Standard and Turbo text-to-video and image-to-video workflows with native audiovisual generation. Create 1–16-second clips at 540p, 720p, or 1080p, animate one image or transition between ordered start and end frames, and control generated sound, background music, and motion amplitude.
Workflows
Text / Image to Video
APIXO Price
$0.04–$0.16 / Sec
Resolution
540p / 720p / 1080p
Duration
1–16 Seconds
Image Input
1–2 Ordered Frames
Create with Vidu Q3
Loading workspace...
Short-form storytelling with integrated motion and audio
Native Audiovisual Output
Vidu Q3 generates visuals and sound together, supporting dialogue, voiceover, effects, and music without requiring a separate uploaded-audio or post-generation synchronization step.
Up to 16 Seconds
APIXO accepts any integer duration from 1 through 16 seconds, providing more room for narrative beats, camera changes, dialogue, and transitions within one generation.
Multilingual Storytelling
Official Vidu materials describe English, Japanese, and Chinese output, including multi-person conversations. Exact wording, pronunciation, speaker attribution, and lip synchronization still require review.
Ordered Frame Transitions
Image modes accept one frame for animation or two ordered images for a transition. The first URL defines the opening frame and the second defines the ending frame.
Generated Audio Controls
APIXO exposes separate `sound` and `bgm` booleans. `sound` controls model-generated audio broadly, while `bgm` separately requests background music. The public documentation does not specify default values or a dependency between the two controls.
Motion Amplitude
Select auto, small, medium, or large movement to influence overall motion intensity. This is not an exact camera path, keyframe, lens, or FPS control.
Balance generation cost with Standard or Turbo routing
Standard Text and Image Workflows
APIXO’s text-to-video and image-to-video enums use the Standard billing group. Choose this route group when its output profile is preferred over Turbo and select the required resolution and duration for each task.
Lower-Cost Turbo Workflows
turbo-text-to-video and turbo-image-to-video use lower per-second rates at every documented resolution. APIXO does not publish the precise upstream checkpoint IDs behind either workflow group.
Vidu Q3 route specifications
Verified controls and delivery behavior exposed through APIXO.
1–5,000 Characters
Prompt
4 Mode Enums
Workflows
5 Text Ratios
Framing
General / Anime
Text Style
1 MP4 URL
Output
Polling / Callback
Delivery
Production workflows suited to Vidu Q3
Multilingual Dialogue Scenes
Prototype short conversations and story beats in English, Japanese, or Chinese with generated voices, ambience, and effects. Review pronunciation, dialogue attribution, vocal consistency, and audiovisual alignment before publication.
Product and Advertising Concepts
Build short product reveals, launch scenes, and narrative advertisements with selectable duration, resolution, framing, and sound. Check product proportions, logos, embedded text, hands, and object contact carefully.
First-to-Last Transitions
Use two ordered images to direct a transition between planned visual states, or animate one still image into a moving scene. Significant changes may reduce reference-frame fidelity or introduce geometry drift.
Anime and Comic Concepts
Use APIXO’s text-mode anime preset to explore comic-drama scenes, short-series ideas, and stylized social clips. Review character positioning, identity continuity, dialogue timing, and multi-character interactions across the result.
Integration guidance for the Vidu Q3 route
Integration Notes
APIXO exposes four workflow enums but does not identify their exact upstream Q3 checkpoints, so Standard must not be presented as confirmed viduq3-pro.
First-and-last-frame generation is implemented inside both image-to-video modes using two ordered URLs; it is not a fifth APIXO mode.
APIXO’s detailed documentation applies aspect ratio only to text modes, although the live form schema may display it as globally required.
APIXO exposes `style` only for text-to-video modes. `movement`, `sound`, `bgm`, and `seed` are route-level controls, but the public documentation does not publish default values for the audio booleans.
Typical processing ranges from 60–120 seconds for short Turbo jobs to 60–180 seconds for Standard tasks; longer or 1080p generations may take 2–4 minutes or more.
Result URLs are temporary, but APIXO publishes no fixed retention period; download and store important MP4 outputs promptly after completion.
Frequently Asked Questions
Total cost equals duration multiplied by the selected rate. Standard costs $0.07, $0.15, or $0.16 per second at 540p, 720p, or 1080p; Turbo costs $0.04, $0.06, or $0.08 per second. Text and image modes share their group’s rates.
APIXO exposes `sound` and `bgm` as separate optional booleans. Disable both when requesting a silent result. The public documentation does not state their default values or whether background music depends on generated sound. No uploaded-audio, source-audio, voice, speaker, language, pronunciation, or lip-sync field is documented.
APIXO requires one or two directly accessible public image URLs and rejects inaccessible or unprocessable files. Its detailed route documentation does not publish an exact format list, file-size ceiling, or dimensional range, so WebP support should not be assumed.
No. APIXO accepts an integer from -1 through 2147483647 for seed-controlled iteration, but a repeated seed does not guarantee deterministic output. The route exposes no negative prompt, CFG scale, camera keyframes, FPS, safety level, or output-count control.
Explore Other Models
Discover more AI models for your next creative workflow
