Vidu Q3 Pro Text-to-Video generates high-quality, audio-capable videos from text (viduq3-pro, 1–16s). Billing follows Vidu's published Q3-pro per-second rates by resolution. Ready-to-use REST inference API on WaveSpeed.
Boşta

$0.25çalıştırma başına·~40 / $10
Vidu Q3 Pro is a fast, versatile text-to-video model that generates high-quality videos from text prompts. It supports multiple resolutions, style presets, motion intensity control, and optional audio generation with background music — perfect for rapid creative iteration and content production.
POST /ent/v2/text2video, model viduq3-pro)Fast generation Pro architecture delivers quick results for rapid prototyping and iteration.
Multiple resolutions Choose from 540p, 720p, or 1080p to balance quality and speed.
Style presets Select from various visual styles to match your creative vision.
Motion control Adjust movement_amplitude to control the intensity of motion in the video.
Audio generation Optional synchronized audio and background music to create complete video content.
Prompt Enhancer Built-in tool to automatically improve your scene descriptions.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the desired video scene |
| style | No | Visual style preset (default: general) |
| resolution | No | Output resolution: 540p, 720p, or 1080p (default: 720p) |
| duration | No | Video length in seconds; 1–16 for Q3-pro (default: 5) |
| movement_amplitude | No | Motion intensity: auto or manual value (default: auto) |
| generate_audio | No | Whether to generate synchronized audio (default: enabled) |
| bgm | No | Include background music (default: enabled) |
| seed | No | Random seed for reproducible results |
Per-second rates below match Vidu Q3-pro standard (peak) pricing for text2video / img2video / start-end2video (source). Off-peak mode uses lower credits (tasks complete within 48 hours; see Vidu docs).
| Resolution | Cost per second (standard) |
|---|---|
| 540p | $0.05 |
| 720p | $0.125 |
| 1080p | $0.15 |
audio flag; this WaveSpeed schema exposes generate_audio (and bgm) — see Text to Video for provider semantics.