audio_detach MCP tool: idempotency_key, jobs_wait, jobs_result
Hosted MCP exposes audio_detach. It needs an idempotency_key, mcp:write under OAuth, then jobs_wait and jobs_result to read the new audio_url.
Agents
The Sume video agent from code: Agent Completions, scheduled runs, MCP tools and timeouts, programmatic tool calling, and guardrails for paid APIs.
Start with: What is a video agent? How Sume defines and runs one
Can ChatGPT make videos from photos? Image to video now
Not with Sora, which OpenAI discontinued. ChatGPT can send a photo's public URL to an image-to-video tool over MCP and get a clip back.
Can ChatGPT make videos with sound? Audio and voice
Yes, through a video tool whose model generates audio. A voice that speaks your script is a second step: text to speech, then lip sync.
Can ChatGPT make long videos? Clip limits and how to join
Not in one clip: generated clips top out at 15 or 30 seconds. ChatGPT can join many clips over one audio track into a render of up to 30 minutes.
Can ChatGPT make videos better quality? Upscaling a clip
With an upscaling tool, yes: ChatGPT can send a clip's public URL to a video upscaler over MCP. For new clips, ask for a higher resolution.
Can ChatGPT make slideshow videos? Stills, voice, one MP4
Yes, through tools: ChatGPT can make the slides, voice the script, and have a timeline tool hold each still for its line in one MP4.
Can ChatGPT make TikTok videos? Vertical clips and limits
ChatGPT can write the hook and, with a video tool over MCP, have a 9:16 clip rendered. Posting it to TikTok is a separate step you do.
Can ChatGPT make music videos? Song, clips, one render
With tools, yes: ChatGPT can have a track generated, a short clip made per section, and the clips cut over the song in one MP4 render.
Can ChatGPT make music? Getting a song or beat as audio
To get a song or a beat as an audio file, give ChatGPT a music tool: in developer mode it can call one over MCP and hand back a link to the track.
Can ChatGPT make product videos from a product photo?
Yes, with a video tool: in developer mode ChatGPT can send your product photo to a video model as the first frame and return a link to the clip.
Can ChatGPT make UGC videos? Script, voice, and lip sync
Not by itself. With a video tool connected in developer mode, ChatGPT can script, voice, and lip-sync a UGC-style clip, confirming paid calls first.
ChatGPT script to video: voice it, then cut to each line
ChatGPT writes the script; tools turn it into video. Voice it word for word, make one visual per line, and cut each to its sentence on a timeline.
Can ChatGPT make videos for free? Plans and per-clip costs
Not for free. Free ChatGPT accounts can't turn on developer mode, and the video tool it calls needs its own paid plan and bills each clip.
Can Claude make videos for free? What each plan allows
Claude outputs text on every plan. Free can add one video tool as a connector, but the tool bills each clip, so the videos themselves aren't free.
Can Claude Cowork make videos? Yes, through a connector
Not by itself: Cowork's models output text. Add a remote MCP video tool as a custom connector and a Cowork task can render clips and images as links.
Can Claude generate transparent images? Only in two steps
Claude can't generate images, transparent or not. Through an image tool it takes two calls: generate on a plain backdrop, then cut out a PNG with alpha.
Can Claude generate multiple images at once? Yes, via a tool
Claude can't draw, but through an image tool one call can ask for several images, up to 4 per model today, and Claude can send one call per scene at once.
Can Claude generate high resolution images? 4K via a tool
Claude can't make images itself. Through an image tool it can ask for a 4K tier on models that list one, then upscale a still up to 4x.
Can Claude create product images? From your photo, via a tool
Claude can't create images, but it can send your product photo to an image tool as a reference and describe the new scene. How it works and its limits.
Can Claude make video ads? Script yes, video via tools
Claude writes the ad's concept and script but outputs text. With video, voice, music and editing tools connected, it can render and assemble the ad.
Can ChatGPT make podcasts? Script, voices and one audio file
ChatGPT can write a podcast script. For a finished episode, give it speech tools over MCP: it voices each host's lines and joins them into one file.
Can ChatGPT create a video of me talking? Photo plus voice
Yes, with a connected tool: in developer mode ChatGPT can voice your script and lip sync a photo of you to it over MCP, then link the finished clip.
Claude Opus 5.5 and paid MCP tools: preview and cap spend with dry_run
Give Claude Opus 5.5 a paid video tool without a surprise bill: dry_run previews cost, max_spend_usd caps a call, idempotency_key stops double submits.
Batched tool calls and video jobs: one jobs_wait for up to 20 clips
Anthropic says Claude Sonnet 5.5 batches tool calls more than Sonnet 5. On Sume MCP, submit several clips in parallel, then wait on all with one jobs_wait.
Give my agent video generation: MCP, REST or Agent Completions?
Three ways to give an agent video generation on Sume: the hosted MCP server, the /v1/videos REST API as your own tool, or Agent Completions for the whole task.
GPT-6 Astra async tool calls: what a slow video job means for agents
OpenAI's GPT-6 guide describes async tool calling with async: true and call_id. How that maps to a video job that takes minutes, and where Sume's job ids fit.
GPT Image 2.5 in Codex: what OpenAI says, and API options
OpenAI says ChatGPT Images 2.5 is available to Codex users. To call GPT Image 2.5 from your own code or agent, Sume offers hosted MCP and a REST API.
MCP tool search: how a long Sume tool list loads in Claude Code
Claude Code loads MCP tools on demand with tool search, which is on by default. What that means for Sume's long hosted tool list and how to prompt for it.
Runway Brand Kits in MCP, and how Sume handles references
Runway MCP agents can now reference Brand Kits, edited only in Runway's app. Sume's docs list no saved kit; you pass references per request.
Video agent API: turn a brief into a finished, edited video
Yes. Video agent APIs that turn a brief into a finished, edited video, compared by input, output, price unit, limits and revisions, and where Sume fits.
How to write a video brief: parts, template, agent tips
A video brief states the deliverable, audience, one message, must-show items, tone, and what done means. A template, and how an AI agent reads it.
PDF to video AI: how to turn a document into a video
PDF to video AI turns a document's text and figures into a narrated video. On Sume today, you extract the text and export the figures as images first.
Agentic video editing: what an AI editing agent does
Agentic video editing means an AI agent plans an edit, runs it with editing tools, and checks the result. What those tools are and what they can read.
HeyGen Video Agent: what it does, its API, and pricing
HeyGen's Video Agent turns a text prompt into a finished avatar video, in the app or via POST /v3/video-agents. Its inputs, outputs, and API price.
Video shot list template: columns, example, AI version
A video shot list is one row per shot: number, what we see, framing, move, length, audio, source. A template to copy, plus the columns AI video needs.
Can Codex make videos? No, but it can call a video tool
No: Codex's docs list image generation but not video. Add a video tool over MCP, such as Sume's hosted server, and Codex can start clips for you.
Can Cursor generate videos? Images yes, video via MCP
Cursor's Agent has a built-in image generation tool but no video tool. To make video from Cursor, connect an MCP server that has one.
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.
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.
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.
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.
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.
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.
ChatGPT text to speech: make an audio file with MCP
ChatGPT Voice speaks its replies. To get your own script as an audio file, add a text-to-speech tool to ChatGPT over MCP in developer mode.
Can ChatGPT make videos? Sora's shutdown and what works now
OpenAI discontinued Sora in 2026. ChatGPT can still start a video by calling a video tool on a remote MCP server in developer mode.
Can Claude make videos? Only by calling a video tool
Claude's output is text, not video. It can still get you a clip by calling a video tool, such as Sume's hosted MCP server added as a connector.
Can Claude generate images? No, but it can call a tool
No: Anthropic says Claude understands images but cannot create or edit them. Connect an image tool over MCP, such as Sume's generate_image.
Can Claude edit videos? Only by calling editing tools
Claude takes text and images, not video, and replies in text. It can still cut, crop, or assemble a clip by calling editing tools over MCP.
Video generation MCP server: how Sume's generate_video works
Sume's hosted MCP server has a paid generate_video tool: a prompt or image in, a job id back, then jobs_wait and jobs_result for the clip.
Agent skills vs MCP: what each does and when to use both
An agent skill is know-how the agent reads when a task matches; an MCP tool is an action it calls on a server. How they differ, and when to use both.
Human in the loop AI agents: where a person approves
Human in the loop means an AI agent stops for a person before steps that matter. How Sume's agent does it in chat, and what replaces it in API runs.
A Claude skill to generate video: what works today
Anthropic's pre-built skills cover documents, not video. A Sume CLI skill lets Claude Code make avatar videos; other clips need MCP or the API.
MCP server for image editing: restyle, cut out, upscale
Sume's hosted MCP server gives agents three image edits: prompt edits from reference images, background removal to a PNG with alpha, and upscales.
MCP prompt injection: limit what a hijacked agent can do
MCP prompt injection gets an agent to call tools nobody asked for. Bound the session instead: fewer tools, read-only by default, confirmed writes.
Difference between an MCP server and an AI agent
An MCP server exposes tools; an agent is the program where a model decides which tools to call. How the work splits, with Sume's server and agent.
YouTube chapter generator: timestamps from a transcript
A YouTube chapter generator turns a transcript into timestamps and titles from 00:00: sentence timings from speech-to-text, topic breaks from an LLM.
Transcribe audio to text with Claude using an MCP tool
To transcribe audio to text with Claude, give it a speech-to-text tool over MCP and a public audio URL, then read the transcript and word timings.
Claude text to speech: make audio files with an MCP tool
For text to speech in Claude, connect a text-to-speech tool over MCP: Claude sends the script and a voice, then hands back a link to the audio file.
Make AI UGC videos with Claude: avatar, voice, lip sync
Claude's models output text. Connect Sume's hosted MCP server with Write on, and Claude can script, voice, and lip-sync a UGC-style avatar clip.
AI image description generator: alt text and captions by API
Send an image to an agent API that can see it and ask for alt text, a title, or a product description as JSON fields. How to run it with Sume.
How to make a video ad with AI: brief, draft, approve, reuse
To make a video ad with AI, brief a video agent on the deliverable, review a draft before the paid render, then save the recipe to reuse it.
Generate images for a website with Claude Code and Sume MCP
Connect Claude Code to Sume's hosted MCP with Write access, preview the cost with dry_run, then generate site images and save them in your repo.
Summarize a video with an API: transcript, stills, then JSON
Summarize a Sume-hosted video: pull stills and a transcript with POST /v1/video-inspect, then send both to Agent Completions with an output_schema.
What is Sume? A video agent platform, its API, and billing
Sume is a video agent platform: brief an agent in chat, save the recipe as a Format, and call it from your backend over one API. Surfaces and billing.
Sume Agent Completions vs Format vs Scheduled runs: request body diff
Sume Format runs, Scheduled runs, and Agent Completions share field names, not rules: spend-cap defaults, null, on_active_run, attachments, and scopes differ.
Prevent overlapping AI agent runs on Sume with on_active_run
Sume's on_active_run field decides what a second run request does while one is in flight: run anyway, record a skipped run, or get a 409 and nothing runs.
MCP vs CLI vs API for AI agents: which Sume interface to use
On Sume, HTTP and the Format API are the primary path for AI agents. Hosted MCP fits remote MCP clients; the CLI fits shell agents and is Avatar-heavy.
MCP tool call timeouts on long-running video jobs: use jobs_wait
On Sume's hosted MCP server, one jobs_wait call holds at most 55 seconds. Wait out long video jobs in slices, batch up to 20 ids, and never resubmit.
Sume MCP tools list: hosted tools grouped by read, write, and paid
The Sume MCP tools list by family: which hosted tools only read, which write, which start paid jobs, and which tool names are not on hosted MCP at all.
Programmatic tool calling on MCP: how Sume's script_run works
script_run is programmatic tool calling on Sume's hosted MCP: a short JavaScript program calls tools in loops or in parallel under call and paid budgets.
Video editing MCP server: let an AI agent trim, filter, and assemble
Sume's hosted MCP server gives AI agents video editing tools: inspect, frames, trim, filter, audio detach, compose, and a Timeline render, each run as a job.
List scheduled agent runs over the Sume API: audit your schedules
List Sume schedules with GET /v1/actions (limit, status, trigger_type), page each run history with a cursor, and read trigger.source to tell cron from API runs.
Agent API with image input and JSON output: Sume Agent Completions
Send images to Sume Agent Completions as input_image parts or attachments, bind an output_schema, and read typed JSON from output when the run completes.
What is a video agent? How Sume defines and runs one
In Sume's docs, a video agent is a sandbox Agent that composes generation tools into a post-ready video. Brief it in chat, or call it over HTTP.
Safe automation for AI agents that call paid APIs
Keep agents read-only by default, keep secrets out of logs, and on hosted MCP send an idempotency_key, preview with dry_run, and cap with max_spend_usd.
Scheduled AI video agent runs: cron, API triggers, and receipts
A Sume schedule is a saved Agents automation that runs on a cron cadence and returns a run receipt. Author it in the dashboard; start and monitor runs by API.
Run the Sume video agent from your backend with Agent Completions
POST /v1/agent/completions runs the same agent as the Sume Agents chat, with tools and media generation, and returns an async run receipt you poll or webhook.