JSON-to-video & AI Video API

Turn JSON into rendered video.

SamAutomation (Sam Automation) is a deterministic video API. Send media, voice-over, captions and timings in one JSON payload, get a finished MP4 back, and generate AI video and images on the same key.

POST /api/function/video-generation/mix-video
{
  "media_list": [
    { "type": "video", "url": "https://cdn.app/clip1.mp4" },
    { "type": "image", "url": "https://cdn.app/logo.png" }
  ],
  "voice_over_url": "https://cdn.app/vo.mp3",
  "captions": [{ "start": 0, "end": 2, "words": "Ship faster" }],
  "settings": { "aspect_ratio": "9:16" }
}
200 OK · queued task_id + MP4 callback URL Get 24 n8n flows (€29)
1 API key
Deterministic JSON-to-video rendering plus AI video and image models.
89 AI models
62 video and 27 image models on one unified job format.
24 n8n workflows
Skip boilerplate node wiring with the Workflow Vault (€29 one-time).

Sound on for the full motion edit.

16-second product tour

From payload to finished video without opening an editor.

Watch the pipeline SamAutomation runs in production: JSON in, a render job queued, a finished MP4 out, plus optional AI footage and n8n callbacks when your stack needs them.

Core rendering engine

The video API for automation

Deterministic, repeatable rendering built for backends and no-code pipelines, not a manual timeline editor. Coming from an editor? Read what a CapCut API can and cannot do, or start with JSON to video and text to video.

01

JSON in, MP4 out

Mix video, images, voice-over and captions from one payload. Simple, loop and advanced renderers for every aspect ratio.

02

Webhooks and status polling

Submit async, receive a task id, poll progress or accept a webhook callback. Built to run unattended in production.

03

Reusable render templates

Save a verified layout as a template and feed it fresh data on each run. Browse the marketplace or publish your own.

04

Captions, baked in

Generate auto-captions from a transcript or script and burn styled subtitles directly into social videos.

n8n & Zapier workflows Social cutdowns at scale Onboarding video Programmatic ads
# 1. Submit a render job
POST /api/function/video-generation/mix-video
# → { "task_id": "a1b2", "status": "queued" }

# 2. Poll progress until finished
GET /api/function/video-generation/progress/a1b2
# → { "status": "done", "video_url": ".../out.mp4" }

# 3. Or push directly to your webhook
"callback_url": "https://your.app/hooks/video"

AI video and image add-on

Need generated footage? Add AI.

Same key, same job pattern. Generate clips and images across 62 video and 27 image models when you lack source footage, then composite them with JSON-to-video. Full model routing is documented on the AI video API page.

Text to video

Describe a scene, get a clip.

Grok Imagine

xAI

xAI text and image to video.

  • Text and image to video
  • Multiple aspect ratios
  • Several style modes
Best for: Fast creative clips, Social-first short video

Grok Imagine Video 1.5

xAI
New

Text, image or up to 4 timed keyframes to video of 1 to 15 seconds, sound always on.

  • Prompt, one image, a loop image, first plus last frame, or up to 4 keyframes with timestamps
  • 480p, 720p or 1080p across eight aspect ratios
  • Native audio is always on; keyframes sit at least 0.33 seconds apart
Best for: Social clips with sound in one pass, Scene changes timed from keyframes

Kling 3.0

Kuaishou

Director-grade text/image-to-video, with a fast tier.

  • Text and image to video with multi-shot storyboarding
  • Native multilingual audio
  • Turbo tier for faster, lower-cost generation
Best for: Short-form ads, Image-to-video product shots

PixVerse V6 Max

PixVerse
New

Film-grade text-to-video with readable on-screen text and native sound.

  • Text-to-video, 1 to 15 seconds, sound on or off
  • 360p up to 1080p and eight aspect ratios
  • Readable on-screen text for ads and product shots
Best for: Ad clips with burned-in copy, Product shots with native sound

Veo 3.1

Google DeepMind
Flagship

Cinematic text/image-to-video with synchronized native audio.

  • Native synced audio — dialogue, ambient sound and music in one pass
  • Up to 3 reference images for character and scene consistency
  • Scene extension to chain shots into longer sequences
Best for: Programmatic ad and social video, Character-consistent multi-shot sequences

Image to video

Animate a still or a first/last frame.

Vidu Q4

Vidu
New

One photo in, a 3 to 16 second clip with sound out.

  • One first-frame image; the clip keeps that image's aspect ratio
  • Generated sound and dialogue; audio on or off costs the same per second
  • 540p up to 4K. For several reference images use vidu-q4-r2v
Best for: Talking character from a single portrait, Animating a product photo

Hailuo 2.3

MiniMax

Image-to-video at standard and pro quality tiers.

  • Image-to-video generation
  • 768p and 1080p tiers
  • 6s and 10s clips
Best for: Animate a product still, Short social clips from images

PixVerse V6 Max Image to Video

PixVerse
New

Animate one image as the first frame, 1 to 15 seconds, with sound.

  • Exactly one image; the clip keeps its shape
  • 360p, 540p, 720p or 1080p, sound on or off
  • Native audio; silent renders cost less per second
Best for: Animating a product still, Turning a photo set into motion shots

Multimodal & reference

Steer with images, video, voice or character refs.

Gemini Omni

Google
Premium

Any-input-to-video with voice and character consistency.

  • Combine text, image, video and voice references
  • Character consistency held across edits
  • Voice and character workflows for personalized presenters
Best for: Mixed-media short-form video, Personalized presenter and avatar clips

Gemini Omni Flash 1.2

Google
New

Fast multimodal clips of 3 to 15 seconds at up to 4K.

  • Four modes: text or reference images, first frame, first plus last frame, or a clip edit
  • Edit an existing clip of up to 15 seconds from a prompt
  • 16:9, 9:16 or auto; up to 6 reference images plus one source video
Best for: Quick iterations at the flash price, Restyling an existing clip into a new cut

Kling 3.0 Motion Control

Kuaishou
New

Transfer motion from a reference video onto your character.

  • Motion transfer — re-animate a character with a reference clip's motion
  • Character identity kept consistent
  • 720p and 1080p output
Best for: Brand mascot performing a referenced gesture or dance, Consistent character animation

Kling 4.0

Kuaishou
New

Text or up to 15 reference items to video with native sound.

  • Subjects: 2-4 images or one character video per item, up to 7 items
  • Up to 3 standalone voice references, 3 to 30 second clips
  • 720p and 1080p; Keyframes variant animates up to 10 ordered frames
Best for: Character-consistent clips from reference photos, Keyframe-ordered story moments

Kling 4.0 Flash

Kuaishou
New

Cheaper Kling 4.0 tier: 720p clips of 3 to 20 seconds with native sound.

  • Text or up to 15 reference items to video, 720p only
  • Each subject declares type image or video and can carry a voice_url
  • Reference videos count towards 2 to 20 seconds combined
Best for: Reference-driven clips at the lowest Kling 4.0 price, Talking character scenes with a bound voice

Seedance 2.0

ByteDance
New

Multimodal video with native audio and multi-shot cuts.

  • Text, image, video and audio references in one call
  • Multi-shot generation with natural cuts
  • Native in-pass audio; Fast tier for quick iteration
Best for: Single-call multi-shot product videos, Reference-driven brand consistency

Seedance 2.5

ByteDance
New

Seedance 2.5 from ByteDance with native audio and reference inputs.

  • Text, image, video and audio references in one call
  • Native in-pass audio
Best for: Reference-driven brand clips, Multi-shot product videos

Avatar & lip-sync

Talking avatars and re-synced footage.

OmniHuman 1.5

ByteDance
Premium

Expressive talking avatar from one image and audio.

  • Audio-driven animation from a single image plus speech
  • Context-aware expression, gesture and head motion
  • Portrait, half-body and full-body framing
Best for: Talking-head spokesperson clips from one headshot, Localized presenters per language

OmniHuman 2.0

ByteDance
New

Talking video from one photo plus your speech audio.

  • One image and a 4 second to 5 minute speech audio track
  • Prompt-steered motion, billed on measured audio length
  • 720p output, portrait to full-body framing
Best for: Spokesperson clips from one headshot and a voiceover, Localized presenters per language

Video Lip Sync

New

Re-sync an existing video's lips to new target audio.

  • Video-to-video: regenerate the mouth region to match new audio
  • Keeps the original footage; swaps only the speech
  • Ideal alongside a translation pipeline
Best for: Dubbing and localization of talking-head footage, Updating a presenter video with new audio

Video editing

Edit, extend and transform existing clips.

HappyHorse 1.1

Alibaba
Featured

Joint audio-video generation with best-in-class multilingual lip-sync.

  • Four endpoints: text, image, reference-to-video and instruction edit
  • Native synced audio with multilingual lip-sync across languages
  • Reference-to-video from multiple images for character consistency
Best for: Talking-character clips with perfect lip-sync, Localized/dubbed video at scale, Multi-reference brand videos

Video Upscaler

New

Bring one existing clip to 1080p, 2K or 4K; ratio, frame rate and audio stay intact.

  • One source clip per job, up to 60 seconds and 50 MB
  • Billed per measured second at the chosen 1080p, 2K or 4K rate
  • The job reserves the resolution's maximum first and books the difference back once the measured length is known
Best for: Lift an older render to a sharper tier before delivery, Sharpen AI clips for a large screen

Wan 2.7

Alibaba (Tongyi)
New

Director-grade suite: generate, reference and edit video.

  • Four modes: text, image, reference-to-video and instruction video-edit
  • First/last-frame control and multi-reference consistency
  • Native audio generation
Best for: Multi-shot brand clips with consistent characters, Edit-in-place revisions to footage

Wan VACE

Alibaba (Tongyi)
New

All-in-one video creation and editing under one model.

  • Unifies text, image and video-to-video in a single framework
  • Reference-to-video, inpaint/outpaint and region edits
  • Character and camera motion control
Best for: Swap or replace a subject in existing footage, Reference-guided edits and extensions

Real AI model output generated through the API, not stock footage.

Model tiers and credit control

Test cheap. Ship premium.

Most model families ship in tiers. Prototype on the Lite or Fast variant for a fraction of the credits, lock your prompt, then switch the model_id to the top tier for production. Same endpoint, same payload.

Nano Banana 2

4.5× cheaper to test
Lite from 4 cr Prototype & iterate
Standard from 9 cr Balanced
Standard from 18 cr Balanced

Prototype on Lite or Fast, then ship on the top tier.

Seedance 2.0

2.3× cheaper to test
Lite from 38 cr Prototype & iterate
Fast from 71 cr Quick drafts
Standard from 86 cr Balanced

Prototype on Lite or Fast, then ship on the top tier.

Veo 3.1

5.5× cheaper to test
Lite from 40 cr Prototype & iterate
Fast from 100 cr Quick drafts
Pro from 220 cr Final production

Prototype on Lite or Fast, then ship on the top tier.

Kling 3.0

1.2× cheaper to test
Fast from 90 cr Quick drafts
Standard from 110 cr Balanced

Prototype on Lite or Fast, then ship on the top tier.

Every model's exact credit cost lives in GET /api/ai/models. Query it before calling so spend never surprises you.

Simple pricing

One plan covers both

Every plan includes deterministic JSON-to-video rendering plus monthly AI credits. The credit count returned by the API is the exact amount you spend. Top up anytime.

Basic
1,450AI credits per month
  • JSON-to-video rendering included
  • Core video and image AI models
  • n8n webhooks and render templates
Choose Basic
Ultimate
4,950AI credits per month
  • Everything in Pro
  • Avatar and lip-sync models (OmniHuman)
  • Highest monthly rendering allowance
Choose Ultimate

n8n & AI Video Workflow Vault

Import 24 production n8n workflows today

Skip weeks of wiring webhooks, retry loops and API payloads from scratch. Pay once with card or iDEAL, get an automatic Stripe invoice and download the ZIP of import-ready JSON workflows immediately.

  • Starter Vault €29 (12 core flows)
  • Agency Vault €79 (all 24 video, ops & SEO flows)
  • One-time license, instant ZIP delivery
Open Workflow Vault (€29) Inspect all 24 JSON flows

Valid n8n .json files with setup README and cURL examples included.

Pay-as-you-go Video API

Need raw AI video clips without a per-seat plan?

Use the UlazAI Video API when your pipeline only needs generated footage. Call Veo 3, Kling, Sora and image-to-video over one REST API, funded by one-time credit packs from €3 or Creator Monthly at €9/mo for 1,000 credits.

  • Veo 3, Kling, Sora & image-to-video
  • Creator Monthly €9/mo (1,000 credits, rollover balance)
  • One-time packs from €3, no per-seat subscription
Open UlazAI Video API View €9/mo & credit packs

Pay-as-you-go credits work across Video Studio, Image Studio and the REST API.

Render your first video today

One key for deterministic JSON-to-video and 89 AI models. Documented, white-label, ready for your pipeline.