Vidu API — 27 Operations and Pricing

The Vidu API gives you one URL-only task endpoint for Vidu video, image, audio, motion, lip-sync, template, and film workflows. OmnAPI handles authentication, credit authorization, task polling, cancellation rules, and webhooks while your application supplies public media URLs.

Use this flow:

1. POST /api/v1/vidu/quote with an operation and input.
2. POST /api/v1/vidu/tasks with the same core fields, optional create-only guards, and an Idempotency-Key.
3. Poll GET /api/v1/vidu/tasks/{taskId} or configure config.webhookUrl.
4. Download completed resources immediately and no later than one hour. Honor an earlier expiry when the returned resource provides one.

Note

OmnAPI does not upload, download, probe, transcode, or store media for this API. Use public https:// URLs. Base64, data:, blob:, and platform upload requests are rejected.

Request envelope

Quote and create share operation, input, and pricingContext. Create also accepts the create-only fields shown below:

Field	Type	Required	Meaning
operation	enum	yes	One of the 27 values in Supported operations.
input	object	yes	The selected Vidu Enterprise v2 request body, nested unchanged except for the restrictions below.
pricingContext.durationSec	number, > 0, max 3,600	conditional	Media duration used when pricing cannot be derived from a URL. Supply it for duration-priced lip-sync, motion, upscale, or edit calls when input.duration is absent.
pricingContext.providerCreditCap	number, 1–100,000	conditional	Vidu-credit authorization reserve required for replace-video, digital-human, template, and template-story.
maxCredits	number, >= 1	create only	Reject creation before debit when the latest OmnAPI quote exceeds this amount.
config	object	create only	Standard priority, tags, metadata, and webhookUrl task config.

Copy the fields from the linked Vidu request-body reference into input, not beside it. Do not copy Vidu’s callback_url / callbackUrl; OmnAPI rejects those fields and uses config.webhookUrl instead. Do not send Vidu credentials. Where Vidu accepts either Base64 or a URL, OmnAPI accepts only a public http:// or https:// URL. For general-film-edit and general-film-compose, include Vidu’s parent id in input; OmnAPI moves it to the fixed Vidu URL path and does not forward it in the JSON body.

Complete input field index

The table below is the complete set of Vidu body fields currently documented by OmnAPI. Names are case-sensitive. “One of” means at least one member of that group must be supplied. Vidu’s callback_url is deliberately absent because OmnAPI rejects it; use config.webhookUrl. Follow the linked operation reference in the next section for model-dependent ranges, media formats, dimensions, and file-size limits.

input is intentionally an open pass-through object in the OmnAPI contract. OmnAPI validates the wrapper, pricing inputs, public-URL-only rule, and callback restriction; operation-level request validation is completed by Vidu. Fields outside this table may be forwarded, but they are not part of OmnAPI’s stable documented contract. This distinction matters to generated SDKs: do not assume the OpenAPI schema statically validates every nested Vidu field.

operation	Required input fields	Optional input fields and nested shape
image-to-video	model: string, images: string[1]	prompt, voice_id, is_rec, bgm, audio, audio_type, duration, seed, resolution, movement_amplitude, payload, off_peak
reference-to-video	model, subjects[], prompt	auto_subjects, audio, audio_type, duration, seed, aspect_ratio, resolution, movement_amplitude, payload, off_peak; each subject requires name and images[], with optional voice_id
start-end-to-video	model, images: string[2]	prompt, is_rec, duration, seed, resolution, movement_amplitude, bgm, audio, payload, off_peak
text-to-video	model, prompt	style, duration, seed, aspect_ratio, resolution, movement_amplitude, bgm, audio, payload, off_peak
reference-to-image	model, prompt	images (0–7 for viduq2, 1–7 for viduq1), seed, aspect_ratio, resolution, payload
text-to-audio	model, prompt	duration, seed
timing-to-audio	model, timing_prompts[]	duration, seed; each timing item uses from, to, and prompt
text-to-speech	text, voice_setting_voice_id	voice_setting_speed, voice_setting_volume, voice_setting_pitch, voice_setting_emotion, payload
voice-clone	audio_url, voice_id, text	prompt_audio_url, prompt_text, payload
lip-sync	video_url, one of audio_url or text	speed, voice_id, ref_photo_url, volume
motion-sync-v1	image_url, video_url	payload
motion-sync-v2	images, video_urls	template (motion_control_2 by default; motion_control_2.5 is accepted), payload
extend-video	model, one of video_creation_id or video_url	images, prompt, duration, resolution, payload
multi-frame-video	model, start_image, image_settings[]	resolution, payload; every image_settings item requires key_image and may include prompt and duration
upscale-video	one of video_url or video_creation_id	upscale_resolution, payload
replace-video	video_url, object, image	prompt, start_from, payload; also requires pricingContext.providerCreditCap
digital-human	model, image, plus the speech/prompt fields required by the selected mode	prompt, audio_url, text, voice_id, resolution, payload; also requires pricingContext.providerCreditCap
prompt-recommendation	images, type[] (template, img2video, or both)	resolution, count (1–10)
template	template, images[]	prompt, seed, aspect_ratio, area, beast, bgm, payload; also requires pricingContext.providerCreditCap
template-story	story, images[]	payload; also requires pricingContext.providerCreditCap
general-film-create	images[], duration (10–180)	prompt, aspect_ratio, payload
general-film-edit	id, job_id, prompt	None
general-film-compose	id, job_ids	None
ad-film-create	images[]	prompt, duration, aspect_ratio, language
ad-film-edit	ad_one_click_task_id, type, prompt	storyboard_video_index (required when type is generate_video), payload
ad-film-compose	ad_one_click_task_id, video_task_ids[], bgm_task_id, narration_task_id	payload
trending-replicate	video_url, images[]	prompt, aspect_ratio, resolution, remove_audio

Complete price matrix

Every Vidu credit is billed at 2 OmnAPI credits. At OmnAPI’s $0.002 public quote benchmark, that is $0.004 or 80% of Vidu’s $0.005 dollar list price; your effective cash cost depends on the credit package you purchase. Direct pricing is separate from the Music Video API. Always use /quote; video rates vary by model, resolution, duration, and off-peak selection.

Example: viduq3-turbo, 720p, 5-second image-to-video uses 55 Vidu credits and quotes 110 OmnAPI credits at the standard rate.

OmnAPI credits = ceil(Vidu provider credits) × 2

The tables below show both quantities so you can calculate a request before calling /quote. “Normal / off-peak” values are shown in that order. Vidu bills whole provider credits; formulas that produce a fraction are rounded up at the provider-credit boundary and then multiplied by 2.

The source rate card is Vidu API Pricing. The OmnAPI amount is the public customer charge, not an internal cost figure. The runtime quote remains authoritative if Vidu changes a supported combination.

Q3 image, text, and start/end video

These rates apply per generated second for image-to-video, text-to-video, and start-end-to-video. Q3 Pro Fast is available only for image-to-video.

Model	Resolution	Vidu credits/s normal / off-peak	OmnAPI credits/s normal / off-peak
Q3 Pro	540p	9 / 5	18 / 10
Q3 Pro	720p	20 / 10	40 / 20
Q3 Pro	1080p	24 / 12	48 / 24
Q3 Turbo	540p	7 / 4	14 / 8
Q3 Turbo	720p	11 / 6	22 / 12
Q3 Turbo	1080p	13 / 7	26 / 14
Q3 Pro Fast (image-to-video)	720p	20 / 10	40 / 20
Q3 Pro Fast (image-to-video)	1080p	25 / 13	50 / 26

Q3 reference-to-video

Model	Resolution	Vidu credits/s normal / off-peak	OmnAPI credits/s normal / off-peak
Q3 Mix	720p	24 / not supported	48 / not supported
Q3 Mix	1080p	29 / not supported	58 / not supported
Q3 Turbo	540p	4 / 2	8 / 4
Q3 Turbo	720p	10 / 5	20 / 10
Q3 Turbo	1080p	13 / 7	26 / 14
Q3	540p	7 / 4	14 / 8
Q3	720p	12 / 6	24 / 12
Q3	1080p	15 / 7	30 / 14

Q2 video generation

In the formulas below, s = ceil(duration seconds). Q2 off-peak is half of the normal Vidu total, rounded up, and is then converted at 2×. Setting audio: true on Q2 image-to-video or reference-to-video adds 15 Vidu credits / 30 OmnAPI credits. Setting is_rec: true on a supported video operation adds 10 Vidu credits / 20 OmnAPI credits.

Operation and model	Resolution	Vidu credit formula	OmnAPI credit formula
Image/start-end · Q2 Turbo	540p	6 + 2 × (s−1)	12 + 4 × (s−1)
Image/start-end · Q2 Turbo	720p	s=1: 8; s≥2: 10 + 10 × (s−2)	s=1: 16; s≥2: 20 + 20 × (s−2)
Image/start-end · Q2 Turbo	1080p	35 + 10 × (s−1)	70 + 20 × (s−1)
Image/start-end · Q2 Pro	540p	s=1: 8; s≥2: 10 + 5 × (s−2)	s=1: 16; s≥2: 20 + 10 × (s−2)
Image/start-end · Q2 Pro	720p	15 + 10 × (s−1)	30 + 20 × (s−1)
Image/start-end · Q2 Pro	1080p	55 + 15 × (s−1)	110 + 30 × (s−1)
Image/start-end · Q2 Pro Fast	720p	8 + 2 × (s−1)	16 + 4 × (s−1)
Image/start-end · Q2 Pro Fast	1080p	16 + 4 × (s−1)	32 + 8 × (s−1)
Text-to-video · Q2	540p	10 + 2 × (s−1)	20 + 4 × (s−1)
Text-to-video · Q2	720p	15 + 5 × (s−1)	30 + 10 × (s−1)
Text-to-video · Q2	1080p	20 + 10 × (s−1)	40 + 20 × (s−1)
Reference-to-video · Q2	540p	15 + 5 × (s−1)	30 + 10 × (s−1)
Reference-to-video · Q2	720p	25 + 5 × (s−1)	50 + 10 × (s−1)
Reference-to-video · Q2	1080p	75 + 10 × (s−1)	150 + 20 × (s−1)
Reference-to-video · Q2 Pro	540p	20 + 5 × (s−1)	40 + 10 × (s−1)
Reference-to-video · Q2 Pro	720p	30 + 5 × (s−1)	60 + 10 × (s−1)
Reference-to-video · Q2 Pro	1080p	85 + 10 × (s−1)	170 + 20 × (s−1)

Q1 and Vidu 2.0 video

Model and operation	Supported output	Vidu credits normal / off-peak	OmnAPI credits normal / off-peak
Q1 image/reference/start-end/text	5s · 1080p	80 / 40	160 / 80
Vidu 2.0 image/start-end	4s · 360p	20 / 10	40 / 20
Vidu 2.0 image/start-end	4s · 720p	40 / 20	80 / 40
Vidu 2.0 image/start-end	4s · 1080p	100 / 50	200 / 100
Vidu 2.0 image/start-end	8s · 720p	100 / 50	200 / 100
Vidu 2.0 reference-to-video	4s · 360p or 720p	80 / 40	160 / 80

Image, audio, and speech

Operation	Scope	Vidu credits	OmnAPI credits
Q2 text-to-image (0 references)	1080p / 2K / 4K	6 / 8 / 10	12 / 16 / 20
Q2 reference-to-image (1–3 references)	1080p / 2K / 4K	8 / 12 / 20	16 / 24 / 40
Q2 reference-to-image (4–7 references)	1080p / 2K / 4K	10 / 16 / 30	20 / 32 / 60
Q1 reference-to-image (1–7 references)	1080p	20	40
Text/timing-to-audio	up to 5s / over 5s through 10s	10 / 20	20 / 40
Text-to-speech	each started 500 characters	10, minimum 10	20, minimum 20
Voice clone	per voice + required TTS preview	300 + TTS	600 + TTS

Caution

Vidu’s current Text to Speech and Voice Clone rows show $0.05 / 500 characters and $1.50 / voice, but their credit column still uses the old pre-10× denomination. OmnAPI converts the dollar column at Vidu’s current $0.005 / credit, resulting in 10 and 300 current Vidu credits. This avoids an under-authorization; reported actual usage is still used for settlement when available.

Video tools, prompt, and motion

Operation	Billing unit	Vidu credits	OmnAPI credits
Prompt recommendation	each started 5 prompts, per requested type	10	20
Lip sync	each started 5 seconds	20	40
Motion Sync V1	each started second · 720p	10	20
Motion Control 2	each started second · 720p	19	38
Motion Control 2.5	each started second · 1080p	34	68
Upscale Pro	each started second · 1080p / 2K / 4K / 8K	10 / 20 / 40 / 160	20 / 40 / 80 / 320

For URL inputs, put the known duration in pricingContext.durationSec. OmnAPI does not download or inspect the source to discover its duration.

Video extension and multi-frame

s = ceil(extension or segment seconds). Multi-frame prices every frame-to-frame segment independently and sums the results.

Model	Resolution	Vidu credit formula	OmnAPI credit formula
Q2 Turbo extension	540p	10 + 2 × (s−1)	20 + 4 × (s−1)
Q2 Turbo extension	720p	15 + 5 × (s−1)	30 + 10 × (s−1)
Q2 Turbo extension	1080p	40 + 10 × (s−1)	80 + 20 × (s−1)
Q2 Pro extension	540p	15 + 5 × (s−1)	30 + 10 × (s−1)
Q2 Pro extension	720p	30 + 10 × (s−1)	60 + 20 × (s−1)
Q2 Pro extension	1080p	60 + 15 × (s−1)	120 + 30 × (s−1)
Multi-frame	up to 9 segments	sum all Q2 segment prices	2 × summed Vidu credits

Film and advertising solutions

General-film and ad-film operations share the same create, edit, and compose rates. ad-film-create uses 15 seconds when input.duration is omitted.

Operation	Billing unit	Vidu credits	OmnAPI credits
General film / Ad film create	1080p · per second	40	80
Edit footage	1080p · per second	40	80
Edit narration	each started 500 characters	10	20
Edit BGM	per second	2	4
Compose film	per call	1	2
Trending replicate	540p / 720p / 1080p · per second	12 / 16 / 20	24 / 32 / 40

Authorization-cap operations

Some template and character workflows do not have a deterministic public rate. The following four operations require pricingContext.providerCreditCap:

Operation	Authorization	Final settlement
template	providerCreditCap × 2 OmnAPI credits	reported Vidu credits × 2
template-story	providerCreditCap × 2 OmnAPI credits	reported Vidu credits × 2
replace-video	providerCreditCap × 2 OmnAPI credits	reported Vidu credits × 2
digital-human	providerCreditCap × 2 OmnAPI credits	reported Vidu credits × 2

OmnAPI deducts the authorized cap at creation and refunds the unused difference when Vidu reports a lower actual total. The cap is a spend authorization, not a quoted fixed price.

Note

The 1.75 OmnAPI credits / Vidu credit customer contract is restricted to the separate Music Video module’s Vidu OneClick component allowlist. It is not a Vidu-family discount and never applies to any Direct operation on this page.

Supported operations

Category	operation	What it does	Exact input body reference
Video	image-to-video	Animate one image.	Image to Video
Video	reference-to-video	Generate video from subject/style references.	Reference to Video
Video	start-end-to-video	Generate between start and end frames.	Start/End to Video
Video	text-to-video	Generate video from a prompt.	Text to Video
Image	reference-to-image	Text-to-image, reference generation, and image editing with 0-7 references.	Reference to Image
Audio	text-to-audio	Generate a sound effect or short audio clip.	Text to Audio
Audio	timing-to-audio	Generate timed audio segments.	Timing to Audio
Speech	text-to-speech	Synthesize speech with a Vidu voice.	Text to Speech
Speech	voice-clone	Clone a voice and synthesize a preview.	Voice Clone
Video edit	lip-sync	Synchronize video speech to text or audio.	Lip Sync
Motion	motion-sync-v1	Transfer motion from a reference video.	Motion Sync
Motion	motion-sync-v2	Use the current motion-control template.	Motion Sync plus OmnAPI’s injected motion_control_2 template
Video edit	extend-video	Extend an existing Vidu creation or public video.	Video Extension
Video edit	multi-frame-video	Generate transitions across multiple keyframes.	Multi-Frame
Video edit	upscale-video	Upscale a video to 1080p, 2K, 4K, or 8K.	Upscale Pro
Video edit	replace-video	Replace an object or region in a video.	Video Replacement
Character	digital-human	Generate a speaking character from an image and text/audio.	Digital Human
Prompt	prompt-recommendation	Recommend image-to-video prompts.	Prompt Recommendation
Template	template	Run a Vidu effect template.	Template
Template	template-story	Run a story template.	Template Story
Film	general-film-create	Create a general-purpose finished film.	One Click General Film — create
Film	general-film-edit	Edit a general-film job; input.id selects the parent.	One Click General Film — edit
Film	general-film-compose	Compose selected general-film jobs; input.id selects the parent.	One Click General Film — compose
Advertising	ad-film-create	Create a finished advertising film.	One Click Ad-Film — create
Advertising	ad-film-edit	Edit advertising footage, narration, or music.	One Click Ad-Film — edit
Advertising	ad-film-compose	Compose selected advertising jobs.	One Click Ad-Film — compose
Trends	trending-replicate	Recreate a trending video format.	One Click Trending Replicate

Real-time Vidu S1 sessions are not included because they require a live RTC connection rather than the asynchronous REST task lifecycle.

Quote

curl -X POST https://api.omnapi.com/api/v1/vidu/quote \
  -H "x-api-key: $OMNAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "operation": "image-to-video",
    "input": {
      "model": "viduq3-turbo",
      "images": ["https://cdn.example.com/frame.jpg"],
      "prompt": "A slow cinematic push-in",
      "duration": 5,
      "resolution": "720p"
    }
  }'

Response:

{
  "operation": "image-to-video",
  "viduCredits": 55,
  "credits": 110,
  "publicUsd": 0.22,
  "pricingMode": "rate-card",
  "pricingVersion": "vidu-direct-public-v1",
  "customerRate": 2
}

credits is the OmnAPI amount to authorize. viduCredits explains the Vidu rate-card quantity. publicUsd is a display estimate; your balance and final settlement remain denominated in OmnAPI credits.

For URL-based tools whose price depends on media length, include the known duration without asking OmnAPI to inspect the file:

{
  "operation": "lip-sync",
  "input": {
    "video_url": "https://cdn.example.com/source.mp4",
    "audio_url": "https://cdn.example.com/voice.mp3"
  },
  "pricingContext": {
    "durationSec": 11
  }
}

Create

curl -X POST https://api.omnapi.com/api/v1/vidu/tasks \
  -H "x-api-key: $OMNAPI_KEY" \
  -H "Idempotency-Key: vidu-i2v-demo-001" \
  -H "Content-Type: application/json" \
  -d '{
    "operation": "image-to-video",
    "input": {
      "model": "viduq3-turbo",
      "images": ["https://cdn.example.com/frame.jpg"],
      "prompt": "A slow cinematic push-in",
      "duration": 5,
      "resolution": "720p"
    },
    "maxCredits": 110,
    "config": {
      "webhookUrl": "https://example.com/webhooks/omnapi",
      "metadata": { "assetId": "asset_123" }
    }
  }'

Response:

{
  "taskId": "task_01J...",
  "status": "PENDING",
  "creditsRequired": 110,
  "viduCredits": 55,
  "pricingMode": "rate-card",
  "pollUrl": "/api/v1/vidu/tasks/task_01J..."
}

Reuse operation, input, and pricingContext from quote, then add maxCredits and config only to create. maxCredits rejects the create before deduction if the current quote is higher. Use a unique Idempotency-Key for each logical job so a network retry cannot create a second paid task.

Poll and download

curl https://api.omnapi.com/api/v1/vidu/tasks/task_01J... \
  -H "x-api-key: $OMNAPI_KEY"

{
  "taskId": "task_01J...",
  "status": "COMPLETED",
  "progress": 100,
  "resources": [
    {
      "id": "res_01J...",
      "index": 0,
      "role": "output",
      "type": "video",
      "url": "https://..."
    }
  ],
  "outputUrlTtlHours": 1
}

outputUrlTtlHours is a conservative cross-operation window, not a promise that the URL expires exactly at that time. OmnAPI does not copy these assets; download them within one hour even when a standard Vidu creation URL would remain valid for up to 24 hours.

The status values are the standard OmnAPI task states: PENDING, PROCESSING, COMPLETED, FAILED, and CANCELLED.

Cancellation and callbacks

POST /api/v1/vidu/tasks/{taskId}/cancel refunds a task immediately before submission. After submission, OmnAPI requests remote cancellation and refunds only after Vidu confirms it. A 409 means cancellation was not confirmed, so the task remains active and was not refunded; keep polling.

Do not put callback_url in input. Use config.webhookUrl so lifecycle events use the standard OmnAPI webhook contract, including signatures and retries.