Guides
Sume guides: the API, Formats, agents, models, media tools and pricing, each answer dated and sourced.
Claude Code MCP project scope: share a server with your team
Claude Code's project scope saves an MCP server to .mcp.json at the repo root for the team to commit. How approval, sign-in, and keys work.
Codex MCP tool timeout: tool_timeout_sec and slow jobs
Codex gives each MCP tool call 60 seconds by default. Raise tool_timeout_sec per server in config.toml, or keep slow media jobs inside the limit.
Best MCP for image generation: 5 servers side by side
Five hosted MCP servers generate images: fal, Higgsfield, Replicate, Runway, and Sume. Their URLs, sign-in, models, and billing, from each vendor's page.
Are MCP servers only for Claude? No, other apps use them too
No. MCP is an open standard, so ChatGPT, Codex, Cursor, VS Code, and Gemini CLI can use the same server. What differs is each client's config and sign-in.
Royalty-free music for YouTube Shorts: what YouTube allows
Use YouTube's Shorts Audio Library or the royalty-free YouTube Audio Library, which YouTube says won't get a Content ID claim. Other music is on you.
YouTube AI content policy: what's allowed, what to disclose
YouTube allows AI videos but requires you to disclose realistic AI-generated or altered content, and won't monetize mass-produced, templated AI videos.
Does TikTok allow AI-generated content? Yes, with a label
Yes. TikTok allows AI-generated content but requires a label on realistic AI images, audio or video. Via the API, is_aigc: true adds the label.
What is AI info on Facebook and Instagram? Meta's AI label
AI info is Meta's label for AI-generated or AI-edited images, video and audio, added when Meta detects AI indicators or when the poster discloses AI.
Text to speech API in Java: pick a voice, save the MP3
Call a text to speech API from Java: choose a voice selector and an audio format, POST the text, wait for the job, then write the MP3 to disk.
How to get a public URL for an image an API can fetch
Host the image where anyone can fetch it over HTTPS without a login: a public storage object, a public bucket URL, or your own site. Then test it.
Remotion with Claude Code: add AI video, voice and music
Set up Remotion's Agent Skills for Claude Code, then load generated clips, narration and music as files, with TTS word timings as captions.
Dreamina vs Seedance: the app and the model it runs
Dreamina vs Seedance: Seedance is ByteDance Seed's video model; Dreamina is a creative app that runs it. When to use the app and when an API.
Runway ML alternatives for AI video: apps and APIs
Runway ML alternatives for AI video: fal, Higgsfield, Kling, Replicate and Sume compared on app vs API, models and billing, read 2026-09-28.
Seedance tokens: how video tokens turn into dollars
A Seedance token measures output size: width × height × seconds × 24 ÷ 1,024. How tokens become seconds and dollars, with per-model rates.
Zero data retention for AI video APIs: what Sume keeps
Zero data retention means a provider stores nothing after it answers. Async AI video APIs can't: the video is a stored file. What Sume keeps, and why.
Multi-shot video generation: what it is and how to do it
Multi-shot video generation returns one clip with several cuts. Which APIs offer it (Kling 3.0, Runway) and how to build it shot by shot on Sume.
AI video generator for commercial use: what the terms allow
Commercial use of AI video is set by each tool's terms and plan, not the model. What Sume, HeyGen, Synthesia, Kling, Higgsfield and Argil allow.
AI agent vs workflow: the difference and when to use each
A workflow runs steps fixed in advance; an AI agent decides its own steps. When each fits, what an agentic workflow is, and how Sume offers both.
TikTok Commercial Music Library (CML): what it covers
TikTok's Commercial Music Library is a pre-cleared set of songs businesses may use free, but only on TikTok. What it covers, and music for other uses.
How does AI video generation work? Inputs, jobs, and limits
AI video generation turns a prompt, and optionally an image, into every frame of a short clip in one async job. What goes in, and why clips stay short.
AI video prompt JSON: what the keys actually do
A JSON prompt for AI video is still text: the model reads keys as words. Length, size and audio are request fields, not keys inside the prompt.
Kling API in n8n: HTTP Request node, auth, and waiting
Call the Kling API from n8n with an HTTP Request node and a Bearer credential, then poll or resume a Wait node. Direct to Kling, or kling-3 through Sume.
n8n MCP Server Trigger: give Claude a video tool
n8n's MCP Server Trigger makes a workflow an MCP server with its own URL. How to connect Claude and attach a tool that generates a video over HTTPS.
Can Claude make YouTube videos? Shorts, long-form, upload
Not by itself: Claude outputs text. With a video tool it can make Shorts clips and long-form cuts, and Claude Code can script the YouTube upload.
Synthesia API documentation: the quickstart, step by step
Synthesia's API docs make a video in four steps: a Legacy (v2) key, POST /v2/videos, poll until complete, then download from a time-limited link.
Seedance vs Grok Imagine: inputs, length, sound and cost
Grok Imagine Video 1.5 animates one image into a silent clip, billed per second. Seedance 2.x adds text, end frames, references and sound, billed by token.
Meta ads bulk upload: push AI videos to your ad account
Bulk upload videos to Meta Ads by API: POST each file_url to the ad account's advideos edge, wait for status ready, then use the video_id in ads.
What is serverless inference? How it works and is billed
Serverless inference means calling a hosted AI model over HTTP with no servers of your own. Providers bill for compute time or for each output.
Do you need a GPU for AI video? Only to run the model
You need a GPU for AI video only if you run the model yourself. A hosted video API needs none: your code sends HTTPS and downloads an MP4.
How to build your own AI video generator (no training)
Build your own AI video generator from a front end, a small backend and a video model API. You don't train a model; your backend holds the key.
React Native API integration: call an AI video API safely
In React Native, call your own backend with fetch and let it hold the API key. React Native's docs warn that anything in the app bundle is readable.
Setting up API calls in FlutterFlow for AI video
Set up a FlutterFlow API call with a Bearer header, make it private so it runs as a Firebase Cloud Function, and poll the video job with a second call.
Send push notifications using the Firebase API for AI video
Send a push with the FCM HTTP v1 API from your server when the video job's webhook arrives: POST messages:send with a short-lived OAuth 2.0 token.
asyncio Semaphore: limit concurrent API jobs in Python
An asyncio Semaphore caps how many coroutines run a block at once. For paid API jobs, hold it from submit to the final status and size it to your limit.
p-limit npm: cap concurrent AI API jobs in Node.js
p-limit runs at most n promise-returning functions at once. For paid AI jobs, wrap the submit and the wait, not just the POST, and set n to your limit.
Circuit breaker pattern in Python for AI API calls
A circuit breaker stops calling a failing API: after repeated failures it opens and fails fast, then lets a trial call through. A Python version.
AWS Lambda maximum concurrency for SQS and AI API jobs
Lambda's SQS maximum concurrency caps how many instances one queue can invoke, from 2 to 1,000. How to set it so AI jobs stay within API limits.
What is a dead letter queue? DLQs for AI job pipelines
A dead-letter queue holds messages that failed processing too many times, so they stop looping and can be inspected. Which AI job failures go there.
httpx timeout: the 5-second default and slow AI API calls
httpx times out after 5 seconds of network inactivity by default. How to set connect, read, write and pool timeouts for slow AI API calls.
Stripe metered billing for AI video: bill each job's cost
Stripe metered billing sums meter events into each customer's invoice. Send one event per finished AI video job, valued at what the job cost.
FLUX.2 API pricing: Pro and Flex cost per image
FLUX.2 API pricing is per image. What FLUX.2 [pro], [flex] and the other variants cost on Black Forest Labs' API, and per image through Sume.
Is Kling AI Chinese? Who owns it and where it's based
Yes. Kling AI is developed by Kuaishou Technology, a Beijing-based company listed in Hong Kong. Who owns it, where its API runs, and other access.
Higgsfield AI vs Runway: apps, API, models and pricing
Higgsfield and Runway both sell a creative app and a video API billed in credits. How their models, API billing and job flow compare, from their pages.
Kling AI alternatives: other models, or Kling elsewhere
Kling AI alternatives: buy Kling 3.0 from fal, Higgsfield, Replicate, Runway or Sume, or switch to another maker's model. Dated table.
Higgsfield alternatives: studio, API and MCP compared
Higgsfield alternatives by the part you use: its studio apps, its API or its MCP link. fal, Kling, Replicate, Runway, Seedance and Sume, dated.
Can you embed a video in an email? What works instead
Mostly no: most email clients strip embedded video. Use a still thumbnail with a play icon that links to the video. How to make one from a video.
What is a video sales letter (VSL)? And making one with AI
A video sales letter (VSL) is a sales pitch delivered as one narrated video, from hook to offer. What goes in one, and how to build it with AI parts.
Can you add videos to Google Business Profile? Rules and tips
Yes. Google Business Profile takes videos up to 30 seconds, up to 75 MB, at 720p or higher, reviewed before they show. How to add one and make one.