API REFERENCE
Date | Update Details |
|---|---|
April 13,2026 | New Model -Support the addition of viduq3-mix、viduq3-turbo、viduq3 model for reference2video -Efficiently generate high-quality audio and video content, making the video content more vivid, vivid, and three-dimensional -You can check the unit price on the pricing page |
February 11,2026 | New Model -Support the addition of viduq3-turbo model for both text2video and image2video and start-end2video - -Support the addition of viduq3-pro model for start-end2video -Efficiently generate high-quality audio and video content, making the video content more vivid, vivid, and three-dimensional -You can check the unit price on the pricing page |
February 04,2026 | [Added Action Synchronization Capability] -Input action reference video+character image to generate a video of the character moving according to the reference video -10 points per second [Add One stop solution Scenario] -It supports One Click For General Films and is applicable to various Internet scenes such as romantic dramas, live dramas, advertisements, documentaries, etc -Support One Click For AD-Films, helping you quickly create product promotional videos -Support One Click For AI MV, upload audio files+images, and generate beautiful MV videos with composite audio scenes for you -Support One Click For Trending Replicate, upload original videos, product or model images, and quickly replicate popular videos for you |
January 27,2026 | New Model -Support the addition of viduq3-pro models for both Wensheng and Tusheng -Efficiently generate high-quality audio and video content, making the video content more vivid, vivid, and three-dimensional -You can check the unit price on the pricing page |
January 27,2026 | New Models - Added viduq2-pro model（Reference To Video） - Support editing and creation of original videos, image reference videos, video reference videos, etc., to achieve repeated creation of video materials - You can check the cost on the pricing page |
December 02,2025 | New Models - Added viduq2-pro-fast model - Faster speed, lowest price, stable quality, supporting Image to Video and Start end to Video - You can check the cost on the pricing page |
December 01,2025 | New Model Abilities - Viduq2 models upgraded new abilities: Reference to image, Text to image and image editing. - The invocation methods and examples of the model’s new abilities can be found in the API references. - You can check the cost on the pricing page |
November 13, 2025 | New Audio&Video Direct Output Capability - Audio&video direct output is now available for Vidu Reference to Video and Image to Video. - You can configure subjects and their spoken lines using the subjects and audio parameters. - For details, please refer to the API documentations.New Digital Human Capability - Upload a digital human image along with text/voice input to generate a talking-avatar video. - This capability supports selecting a custom voice. - For more information, please see the API documentation.Vidu Q2 Duration Upgrade - The Vidu Q2 model now supports 9-second and 10-second durations. - This duration upgrade applies to Text to Video, Reference to Video, and Image to Video interfaces. - Pricing for the new durations can be found in the pricing . |
November 3, 2025 | Important Update – Vidu Credit Inflation⚠️ Must read! Major update! - Starting November 3, 2025, all credits on the Vidu open platform will undergo a 10× denomination adjustment. - Your credit balance and all credit consumption across APIs will be multiplied by 10. - This adjustment only changes the numerical denomination — the actual value of your credits remains the same. - For details, please refer to the Credit Inflation Notice.New Video Replacement API - You can now use this feature to replace people, objects, or animals in a video with specified content. - Click Video Replacement Example to view sample results. - Check the Audio Generation API for detailed usage and parameters. New Multi-Frame API - You can now set multiple keyframes to achieve smooth transitions and scene continuity between different scenes. - Suitable for long-form videos with multiple scene transitions; supports uploading up to 9 keyframe images. - For detailed usage, please refer to the corresponding API documentation. New Parameter - Added new parameter: is_rec . - This parameter can provide you with recommended prompts to generate videos. - This applies to Image to Video and Start end to Video. - Costs 10 points for each call. |
October 30, 2025 | New APIVidu Text to Speech and Vidu Voice Clone are lunched: - Choose from hundreds of voice styles with customizable emotion, speed, and tone. - Clone your own voice for personalized audio generation. - Check the Audio Generation API for detailed usage and parameters. |
October 21, 2025 | New Model Abilities - Viduq2 models upgraded new abilities: Reference to video, Text to video and Video extension. - The invocation methods and examples of the model's new abilities can be found in the API references. - You can check the cost on the pricing page |
September 24, 2025 | New Models - Added viduq2-pro and viduq2-turbo models - Faster speed, better quality, supporting Image to Video and Start end to Video - You can check the cost on the pricing page |
September 17, 2025 | New Parameter Enhancement - The prompt parameter in the request body now supports up to 2000 characters. - This applies to Image to Video, Reference to video, Start end to Video, Text to Video, Template and Reference to Image. You can check the API documentations for more details. |
September 16, 2025 | New Request URLStarting from September 16, 2025, the request address for Template will be updated as follows: - Original address: https://api.vidu.com/ent/v2/template2video - New address: https://api.vidu.com/ent/v2/template Note: This change does not affect the way template2video is called. You can continue using the original address to initiate requests. |
September 11, 2025 | New Templates - Scenario Example Center added 7 templates - "Pokémon Transformation", "Mini Clone Pickup", "Werewolf Transformation", "Monster Hunter", "High-speed Running - Pet", "Anywhere Resize Kiss - Q1 10s", "Anywhere Resize Kiss - 8s" |
September 8, 2025 | New Feature - Image Task: Added reference image generation - Supports uploading 1–7 images - Image resolution up to 1080p - Costs 20 points per useNew Templates - Scenario Example Center added 5 multi-parameter image generation templates - "Product Background Replacement", "Custom Figure Transformation", "Necklace Wearing", "Character Holding Product (Beauty & Personal Care)", "Character Holding Product (Beverages & Alcohol)" |
August 26, 2025 | New Feature - Video Task: Added reference video generation - Supports uploading 1–7 images - Supports selection of viduq1, vidu2.0, vidu1.5 models |
August 7, 2025 | New Parameter - Video Task: Added off-peak mode off_peak - Using off-peak mode reduces credit cost by 50% - Now supports image-to-video, reference-to-video, text-to-video, and start end to video |
July 28, 2025 | New Capability - Other Task: Added lip-sync capability - Input text/audio to precisely match lip movements in video- Supports free choice of voice tone- 5s video costs 20 credits |