Guides
Sume guides: the API, Formats, agents, models, media tools and pricing, each answer dated and sourced.
Direct response video ads: what they are and how to make them
A direct response video ad asks for one action now, such as buy or sign up, and is judged by that response. Its structure, and how to make variants with AI.
YouTube multi-language audio: add dubbed tracks, made with AI
YouTube multi-language audio lets one video carry dubbed tracks you upload yourself. The rules, the upload steps, and how to make each track with AI.
Restaurant video advertising with AI, from your own photos
Restaurant video ads without a shoot: animate your own dish photos into short clips, add a voice-over and music, and export a vertical cut and a loop.
Runway Act-Two: what it does, API inputs and cost
Runway Act-Two applies an acted performance from a 3–30 second video to a character image or video. API fields, credit cost, and a Sume option.
Kling vs Runway: models, clip limits and API prices
Kling's API sells only Kling models; Runway's sells Gen-4.5 and Aleph 2.0 plus other labs' models. Clip limits, audio and per-second prices compared.
Kling 3.0 vs Kling 3.0 Omni: inputs, limits and price
Kling 3.0 and 3.0 Omni share 3–15 s clips up to 4K with native audio. Omni adds reference and edit videos; 3.0 adds Motion Control. Prices compared.
Kling 3.0 prompt guide: length, shots, dialogue, negatives
A Kling 3.0 prompt can run to 3,072 characters and include negative wording. Kling's rules for shot lists, dialogue, languages and Elements.
How to get a Kling AI API key and authenticate requests
Create a Kling AI API key in the developer console, copy it once, and send it as a Bearer token. Legacy endpoints use an Access Key JWT instead.
Runway Gen-4.5 vs Seedance 2.0: inputs, length and price
On Runway's API, Gen-4.5 makes 2–10 s clips for 12 credits a second; Seedance 2.0 makes 4–15 s clips with audio for 36–150 credits a second.
fal AI vs Runway: a model host or a model maker's API
fal runs 1,000+ models from many labs and bills video per second or per video. Runway's API offers its own Gen-4.5 and more, billed in $0.01 credits.
Arcads vs Creatify: AI actor ads or URL-to-video ads
Arcads builds ads from your script and 1,000+ AI actors on monthly plan credits. Creatify turns a product URL into a video ad; API plans start at $99.
Higgsfield API key: how to get one and send it
A Higgsfield API key is a key ID plus a secret made in Higgsfield Console, sent together in one Authorization: Key header from server code only.
What is an MCP server? A plain definition with examples
An MCP server is a program that gives AI apps tools, data, and prompt templates through the Model Context Protocol. How it works, with examples.
Local vs remote MCP server: stdio or Streamable HTTP?
A local MCP server runs on your computer and talks over stdio; a remote one runs elsewhere and is reached by URL over Streamable HTTP. How to choose.
MCP SSE vs Streamable HTTP: which transport to use
SSE is MCP's older, deprecated HTTP transport; Streamable HTTP replaced it with one endpoint that takes every message as a POST. Which to choose.
MCP tools vs resources vs prompts: who controls each
MCP tools are called by the model, resources are attached by the app, and prompts are picked by the user. What each one is for, and how to choose.
How to test an MCP server: Inspector, Postman, or curl
Test an MCP server with the MCP Inspector: connect, sign in or add an auth header, list tools, and call a read-only one. Postman and curl work too.
Remote MCP server URL: what it is and where to find it
A remote MCP server URL is the HTTPS address of a server's MCP endpoint. Where to get one, where to paste it, and why it isn't a page to open.
MCP vs function calling: how they differ and fit together
Function calling lets a model ask your app to run a function you defined; MCP puts tools on a server any client can discover. How they fit together.
MCP vs REST API: what's the difference and when to use each
A REST API is endpoints your code calls; MCP lets an AI app discover and call a server's tools at runtime. How they differ, and when to use each.
MCP error codes: what -32601, -32602, and -32001 mean
MCP error codes are JSON-RPC codes. What -32700 to -32603 mean, why -32001 is a client-side timeout, and how a failed tool call differs from both.
Image generation MCP server: how Sume's generate_image works
Sume's hosted MCP server has a paid generate_image tool: a prompt in, a job id back in milliseconds, then jobs_wait and jobs_result for the images.
Stateless MCP server: sessions, Mcp-Session-Id, and handles
A stateless MCP server keeps no session between requests. What Mcp-Session-Id does, what 2026-07-28 removed, and where state goes instead.
MCP JSON config: what's in mcp.json and why clients differ
An MCP JSON config lists servers by name: a command for local ones, a URL and headers for remote ones. Why the key names differ between clients.
MCP tool call result structure: content, structuredContent
An MCP tool call result has a content array, optional structuredContent, and isError. What goes where, how images travel, and how errors look.
MCP tool description: what to write and how long it can be
An MCP tool description is the text a model reads to pick and call a tool. What the spec says, where Claude Code cuts it short, and what to write.
Copilot CLI MCP server: add Sume with copilot mcp add
Add a remote MCP server to GitHub Copilot CLI with copilot mcp add: Sume's hosted MCP, a key header or OAuth, and a timeout above 55 seconds.
Agno MCP server: give an Agno agent Sume's hosted tools
Connect an Agno agent to Sume's hosted MCP server with MCPTools, an API-key header, a tool allowlist, and timeout_seconds raised from 10.
Hermes Agent MCP server: add Sume in config.yaml
Add Sume's hosted MCP server to Hermes Agent under mcp_servers in config.yaml, with an API-key header or OAuth, and paid tools behind approval.
AutoGen MCP workbench: connect McpWorkbench to Sume
Use AutoGen's McpWorkbench with Sume's hosted MCP server: StreamableHttpServerParams, an API-key header, a 60-second timeout, and fewer tools.
Langflow MCP client: add Sume's hosted MCP server
Use Langflow as an MCP client for Sume's hosted server: register it with a Bearer global variable, then wire MCP Tools into an Agent.
AnythingLLM MCP server: add Sume as a streamable server
Add Sume's hosted MCP server to AnythingLLM in anythingllm_mcp_servers.json with type streamable and a key header, then refresh Agent Skills.
LibreChat MCP server: add Sume in librechat.yaml
Add Sume's hosted MCP server to LibreChat under mcpServers in librechat.yaml: streamable-http, a Bearer key header, and requiresOAuth set to false.
Kilo Code MCP server: add Sume in kilo.jsonc
Add Sume's hosted MCP server to Kilo Code under the mcp key in kilo.jsonc: type remote, the Sume URL, and an API key header or an OAuth sign-in.
Microsoft Agent Framework MCP: connect an agent to Sume
Connect a Microsoft Agent Framework agent to Sume's hosted MCP server with MCPStreamableHTTPTool, a key header, allowed_tools, and approval_mode.
Continue MCP server: add Sume in .continue/mcpServers
Add Sume's hosted MCP server to Continue with a YAML block in .continue/mcpServers: type streamable-http, the URL, and a key from a secret.
CrewAI MCP server: connect an agent to Sume's tools
Give a CrewAI agent Sume's hosted MCP tools with MCPServerHTTP in the mcps field: a Bearer key header, a tool filter, and short jobs_wait slices.
LlamaIndex MCP: load Sume's hosted tools into an agent
Load Sume's hosted MCP tools into a LlamaIndex agent with BasicMCPClient and aget_tools_from_mcp_url, a Bearer key header, and allowed_tools.
Dify MCP client: connect Sume's hosted MCP server
Dify connects to remote MCP servers from Integrations > Tools. Add Sume's hosted MCP by URL, then sign in with OAuth or send an API-key header.
Android Studio MCP server: add Sume to Gemini's agent
Add a remote MCP server to Gemini in Android Studio: enable MCP Servers, add Sume's httpUrl with an API-key header, and approve its tool calls.
IntelliJ GitHub Copilot MCP: add Sume in mcp.json
Add an MCP server to GitHub Copilot in IntelliJ IDEA: Agent mode, Add MCP Tools, and a servers entry for Sume's hosted MCP with an API-key header.
Strands Agents MCP: connect an agent to Sume's MCP server
Connect a Strands agent to a remote MCP server with MCPClient: Sume's hosted MCP URL, an API-key header, and tool_filters to keep paid tools out.
How to add MCP to Devin: connect Sume's hosted server
Add a custom MCP server to Devin in Customize > MCPs: HTTP transport, Sume's hosted MCP URL, an Authorization header or OAuth, then Test tools.
Azure AI Foundry MCP tool: connect an agent to Sume
Add an MCP tool to an Azure AI Foundry agent: a Custom keys connection for Sume's API key, then server_url, allowed_tools, and require_approval.
How to make an AI voiceover: from script to audio file
Make an AI voiceover in five steps: write the script, pick a voice, generate the speech, check its length, and download the file. The Sume API way.
Text to speech in Japanese: set the language to ja
For Japanese text to speech, send the script in kana and kanji and set the language to ja. Left out, Sume can read a kanji-only line as English.
Text to speech pronunciation: how to fix wrong words
Fix text to speech pronunciation: set the text's language, use a voice recorded in it, and respell tricky words. What Sume's TTS API checks for you.
Text to speech time calculator: estimate, then measure
Estimate speech time as word count divided by a speaking rate, then measure the real file: Sume's TTS reports its duration with word timestamps.