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.

Claude can't make a YouTube video by itself: every current Claude model outputs text. Connected to a video tool, Claude can script a Short, generate its clips, and get them joined into one file, and Claude Code can write and run the upload script. Publishing still goes through your channel's OAuth consent and the YouTube Data API.
Claude facts come from Anthropic's Models overview and Claude Code docs; YouTube facts from its Shorts help and Data API pages; Sume facts from the MCP overview, Video generation, avatar video and Timeline 1.0 docs. All read on 2026-09-28. The generic answer is in Can Claude make videos?
What can Claude do for a YouTube channel without a tool?
Anthropic lists text and image input, text output, vision, and tool use for all current models. So on its own Claude writes: the script, the hook, the title and description, a shot list, and the prompt each clip needs. Tool use is what turns that text into a render.
Can Claude make YouTube Shorts?
Yes, with a tool. YouTube counts a square or vertical video up to three minutes as a Short. One generated clip is much shorter, so a Short longer than one clip is several clips joined on one soundtrack.
| Piece | Limit |
|---|---|
| YouTube Short | Up to 3 minutes, square or vertical |
| YouTube long-form | YouTube suggests a wider ratio such as 16:9 |
| One generated clip on Sume | Up to 15 s; seedance-2.5 and wan-3.0 up to 30 s |
| One avatar clip on Sume | 4–60 s from a script, default 9:16, 720p; English speech in current code |
| One Timeline 1.0 render | 1–1800 s audio spine, 1–200 clips |
Can Claude make long-form YouTube videos?
Yes, as an assembly job. Sume's Timeline 1.0 joins one audio spine and ordered clips, within the limits in the table above, into one MP4 at $0.10 per output minute. Every URL must be a Sume-hosted file, such as an earlier Sume job's output. In current code the render keeps sound only from the spine and an optional soundtrack, so put the narration on the spine; each clip's own audio is dropped.
Claude Code fits this work: Anthropic describes it as a tool that reads your codebase, edits files, and runs commands, so it can keep the script, the clip list, and the render request in a project you can rerun. For avatar-led episodes, see AI avatar for YouTube videos.
How does Claude get a video tool?
Through a remote MCP server, such as Sume's hosted server at https://mcp.sume.com/mcp. Can Claude make videos? has the Claude Code and connector setup. Over OAuth the server stays read-only until you opt in to mcp:write at consent. Sume's docs treat hosted MCP as a working client but not the primary path; for an unattended channel pipeline, call the HTTP API from your own code.
Can Claude upload the video to YouTube?
Yes, with your consent. Sume's tools make the file; publishing is a separate call to YouTube's videos.insert method, which needs OAuth authorization with a scope such as https://www.googleapis.com/auth/youtube.upload, which you grant for your channel. Claude Code can write that script, but you run the consent step.
YouTube's page adds that videos uploaded through videos.insert from unverified API projects created after 28 July 2020 are restricted to private viewing until the project passes an audit. Automate YouTube Shorts with AI covers the upload quota and a scheduled pipeline.
Sources
Related posts
More in Agents
- 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.
- 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.
- 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.
Written by Sume