The creative memorypipeline.
Official Partners with BytePlus, a ByteDance companyThe long-term memory layer for AI creative work.
An OS for creative state. Your agent finally remembers every character, scene, preset, and asset it creates. Not another storage bucket. A memory system your models can think with.
BytePlusOfficial Partners with BytePlus — ByteDance's AI infrastructure, used at TikTok scale
Your agent has amnesia
Every session reset, your AI agent forgets every character, scene, and asset it created. AI has working memory. Nobody gave it long-term memory. Until now.
Generation complete
Same character, perfect consistency. 12 credits.
Every AI content API breaks the same way
Session resets. Hallucinated URLs. Budget burn. We fixed all six.
"Session ended. All context lost."
Chat resets, your agent forgets every asset it created. Starts from scratch every time.
Synts fix: Persistent variables & history
Characters, scenes, and every generation are saved permanently. Your agent picks up exactly where it left off via @ninja1, even in a new session.
"Here's your image at cdn.fake/img.png"
Agents hallucinate file URLs, reference IDs, and asset paths that don't exist.
Synts fix: Real uploadIds on every output
Every generation returns a permanent uploadId. No URLs to hallucinate. Reuse across unlimited requests without re-uploading.
"Same character" looks different every time
Without a reference system, agents re-describe characters from memory. The output drifts with every prompt.
Synts fix: Variables with up to 14 reference images
Save a character once, reference it by name. The model gets the actual image data every time, not a text description. Consistent output across sessions.
Agent burns through your entire budget
Most APIs have no cost visibility. Agents loop, retry, and generate without knowing what anything costs.
Synts fix: Credit checks & cost tables via API
Your agent can check the balance and see exactly what a job will cost before submitting. Cancel any job with automatic credit refund.
5 APIs, 5 auth tokens, 5 billing dashboards
Image from one provider, video from another, TTS from a third. Your agent needs to juggle authentication, formats, and billing across all of them.
Synts fix: One key, every modality
Image, video, lip sync, motion transfer, TTS. One auth token, one credit balance, one spec file. Your agent learns one API and gets everything.
Repeating the same prompt + settings every time
Agents reconstruct the full prompt, model, resolution, and references from scratch on every request. One small drift and the output is off.
Synts fix: Presets lock everything in
Bundle prompt template, model, resolution, and asset references into a preset. One API call, identical output every time. Build once, generate thousands.
Swipe to see all 6 fixes
Works with your agent out of the box
MCP-native from day one. Claude Code, OpenClaw, ChatGPT, Cursor, Windsurf—any MCP-compatible agent. Three steps, zero code.
Get your API key
Sign up and create an API key from your workspace settings. Free tier included.
pk_live_your_key_hereDownload the document
Download the OpenAPI document from the docs and drop it into your agent. It picks up every endpoint automatically.
Claude Code
ChatGPT
Cursor
OpenClaw
WindsurfGenerate
Your agent now has native access to image, video, lip sync, motion transfer, and TTS. Just ask it.
"Generate a 4K image of @ninja1 in a neon city"
Swipe through the 3 steps
Drop it into your agent, add your API key. Every endpoint becomes a tool automatically.
Build on the
memory layer
The first API where your AI's creative state persists. Characters, scenes, presets, history, and assets — all addressable, all reusable, all remembered. A memory system your models can think with, not another generation endpoint.
Long-term memory primitives
Characters, scenes, brand assets — saved once, referenced by @mention, reproduced on demand with presets. Your agent's creative state, persistent and addressable. No other API has this.
One key, every modality
Image, video, lip sync, motion transfer, TTS. One auth token, one credit balance.
Production-ready infrastructure
Job queuing, cancel with auto-refund, credit checks, rate limiting, recall windows — everything your pipeline needs, built into the memory layer.
Works with AI agents
Plug into Claude, OpenClaw, or any agent as a tool. Give your AI creative capabilities.
One-call lip sync
OmniHuman accepts raw text directly. No separate TTS step. One request turns an image + text into a talking head video.
Up to 14 reference images
Most APIs allow 1–3. Pass up to 14 reference images per generation for stronger style and character consistency.
Credit transparency
Check your balance and get the full cost table via API before submitting any job. No surprises.
POST /api/generation/image
{
"prompt": "the @ninja1 in a neon cityscape",
"resolution": "4k",
"aspectRatio": "16:9",
"n": 1,
"referenceUploadIds": ["550e8400-..."]
}
// Up to 14 reference images
// Sequential batch mode (up to 15 images)
// Output: jpeg, png, webpPOST /api/generation/video
{
"prompt": "Clouds rolling over mountains at sunrise",
"resolution": "1080p",
"duration": 5,
"ratio": "16:9",
"audio": true,
"referenceImageUrls": ["https://..."]
}
// 2–12 seconds, up to 1080p
// Image-to-video with reference frames
// Audio generation includedPOST /api/generation/omnihuman
{
"imageUrl": "https://cdn.example.com/avatar.png",
"ttsText": "Hello! Welcome to our platform.",
"ttsVoiceId": "voice_en_us_01",
"outputResolution": 1080
}
// Lip sync from audio OR inline TTS
// No separate TTS step needed
// Frame-accurate mouth movementPOST /api/workspace/variables
{
"name": "ninja1",
"slug": "ninja1",
"type": "image",
"description": "Main character"
}
// Then use in any prompt:
// "the @ninja1 exploring @jungle, 4k"
// Works across image, video, all typesPOST /api/generation/presets
{
"name": "Product Shot",
"promptTemplate": "{{product}} on {{surface}}, studio",
"generationType": "image",
"defaultSettings": {
"resolution": "2k",
"aspectRatio": "1:1"
}
}
// Template with {{variables}}
// Locked model + settings
// One-click repeatable generationGET /api/generation/jobs/job_abc123
{
"success": true,
"data": {
"id": "job_abc123",
"status": "COMPLETED",
"jobType": "IMAGE_GENERATE",
"resultUrl": "https://cdn.synts.ai/...",
"creditsCost": 150,
"createdAt": "2026-04-06T..."
}
}
// Filter by status, type, model, date
// Cancel with auto credit refundSimple credit-based pricing
One credit system for every modality. Pay for what you use, scale as you grow.
Starter
then $25/mo after first month
less than $0.63 a day
For builders getting started with AI content
- 15,000 base credits
- 2,500 reward credits(See FAQ)
- Up to 2K images / 720p video
- 10 GB storage
- 30-day history
- API access (5 keys)
- Analytics dashboard
Pro
then $49/mo after first month
less than $1.17 a day
For power builders shipping content daily
- 45,000 base credits
- 12,500 reward credits(See FAQ)
- Up to 4K images / 1080p video
- 100 GB storage
- 90-day history
- Priority support
- Custom branding
Max
then $79/mo after first month
less than $2.17 a day
For studios and teams creating at volume
- 75,000 base credits
- 25,000 reward credits(See FAQ)
- Up to 4K images / 1080p video
- 250 GB storage
- 180-day history
- Priority support
- Custom branding
- All Pro features
Common questions
On paid plans, full ownership and commercial rights transfer to you. Marketing, products, client work, resale, anything. When you create content on Synts, you're the one making the creative decisions: choosing the prompt, selecting parameters, and directing the output. We treat you as the owner. Free tier content is licensed for personal use only.
Yes. You are solely responsible for the content you create using Synts and how you use it. Synts provides AI tools and you provide the creative direction. That means it's on you to make sure your content doesn't infringe anyone's copyright, defame a real person, violate data protection laws, or break any other applicable laws. We implement safety filters and content moderation, but no automated system is perfect. If your use of the platform results in a legal claim, you (not Synts) bear that responsibility. See our Terms of Service for full details.
Most AI tools lock you into a single model or give you a raw API with no workflow around it. Synts selects and integrates the best-in-class models (Seedream for images, Seedance for video, OmniHuman and DreamActor for animation) and builds a unified workflow on top. Images, video, lip sync, and character consistency all share one credit balance in one place. We also expose everything as an API, so teams can build custom pipelines and automate content at scale. The value isn't any one model, it's the intelligent layer that connects them all.
Yes. Starter plans and above include API access. Starter gets 5 keys at 60 RPM, Pro gets 20 keys at 300 RPM, and Business plans scale up to unlimited keys at 3,000 RPM. It's a standard REST API with variables, presets, job management, and long-term memory built in. Plug it into your stack, automate your pipeline, and scale without bottlenecks. Docs are available from your dashboard.
Cancel anytime from your account settings. No lock-in, no questions asked. If you subscribe and haven't used any credits within the first 24 hours, you can request a full refund at support@synts.ai. Once credits are used, the subscription is non-refundable. It's your responsibility to manage your subscription. We don't issue refunds for forgetting to cancel.
Your prompts and generated content are yours. We don't use your prompts to train models, and we don't share your content with third parties. Generated images and videos are stored securely and only accessible to your account. You can delete your data at any time.
Any paid subscriber can buy top-up credit packs from their dashboard: Lite ($10 / 6,500 credits), Standard ($25 / 18,000 credits), or Plus ($50 / 40,000 credits). Business users have larger packs available. Pack credits never expire. Monthly subscription credits reset each billing cycle.
1 credit = $0.001, so 1,000 credits = $1. Every action on the platform costs a flat number of credits: image generation starts at 50 credits, video generation at 50 credits per second, and costs scale with resolution. Your monthly plan refreshes credits each billing cycle. You can also top up with one-time credit packs that never expire.
Log in daily, earn free credits. Higher plans earn more per day. Starter earns up to 5,000/mo, Pro up to 15,000/mo, and Max up to 25,000/mo. Hit login streaks at 3, 7, 14, and 30 days for extra bonuses. Reward credits reset each billing month, so use them while you have them.
Subscription credits (both your base credits and reward credits) reset every billing cycle. Unused ones don't roll over. Credit packs purchased separately never expire and stay in your account until you use them.
Images up to 4K resolution, AI video up to 1080p, enterprise-grade lip sync from any audio input, and consistent AI characters that look the same across every generation. One platform, one credit system. No jumping between five different tools to get the job done.
Get your API key from settings, paste the API docs into your agent, and tell it what you're building. That's it. Your agent reads the docs, learns every endpoint, and can start using Synts as part of your workflow.
Email support@synts.ai or join our Discord community and create a support ticket for faster response. Business and Enterprise plans include priority support with dedicated endpoints and team management.
Stop stitching together
five different APIs
One endpoint. One credit system. Every modality. Variables, presets, job management, and long-term memory included. Start building in minutes.
500 free credits. No credit card required. Full commercial rights on paid plans.