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.

Partly: ChatGPT can write a TikTok hook and script, and with a video tool connected in developer mode it can have a vertical 9:16 clip rendered and hand you the file. Posting to TikTok is a separate step that you do yourself or automate elsewhere.
ChatGPT reaches a video tool through developer mode, which gives it full MCP client support; How to add an MCP server to ChatGPT covers setup. TikTok's length rule comes from its media transfer guide; Sume's come from Video Generation and Timeline 1.0. All were read on 2026-09-29. Sume has no official ChatGPT connector, and its basics page says hosted MCP still works but is not part of the primary path today.
Which parts of a TikTok can ChatGPT do?
TikTok's media transfer guide says all TikTok creators can post 3-minute videos, while some can post 5- or 10-minute videos. TikTok video specs for API uploads and ads lists TikTok's other numbers and maps a Sume file to them. What ChatGPT can do with Sume's hosted MCP tools:
| Part | Who does it | Limit |
|---|---|---|
| Hook and script | ChatGPT itself | None from Sume |
| One vertical clip | generate_video with aspect_ratio: "9:16" | 30 seconds on seedance-2.5 and wan-3.0; 15 seconds on every other catalog model |
| A longer cut from several clips | timeline_create | 1080×1920 MP4 by default, up to 1,800 seconds |
| Posting to TikTok | You, or your own automation | No hosted MCP tool publishes to TikTok |
How does ChatGPT make a vertical clip?
With Sume's generate_video tool, ChatGPT sends a prompt with aspect_ratio: "9:16". Each model lists the ratios it accepts in supported_aspect_ratios, and ChatGPT can check them with video-router_models. In current code the tool asks for audio unless you ask for a silent clip.
A longer TikTok is several clips joined with timeline_create. Only files Sume already hosts for your workspace can go on the timeline, and the render's sound comes from its audio track, not from each clip. Can ChatGPT make long videos? covers the join.
Use the Sume app's generate_video tool: a 9:16, 10-second
clip of hands unboxing a ceramic mug on a wooden desk, soft
morning light, handheld feel. Run dry_run first and show me
the cost. Then wait for the job and give me the video link.Can ChatGPT post the video to TikTok?
Not through Sume's tools: none of the hosted MCP tools listed in Sume's docs publishes to TikTok. The finished clip is a Sume-hosted artifact under media.sume.com; download it and upload it in TikTok, or send it through TikTok's Content Posting API from your own automation. n8n upload to TikTok with the HTTP Request node shows one way.
What does it cost, and what should I check?
- Each clip is billed per job from your Sume workspace balance at the provider's list price × 1.25, plus a 5.5% agent fee by default.
dry_run=truepreviews the cost without submitting. - ChatGPT asks you to confirm write actions by default, so each paid call waits for your approval.
- Hosted MCP cannot read files from your laptop; a photo you want to start from must be at a public HTTPS URL.
- Nothing here promises views or reach. Watch the clip before you post it.
Sources
Related posts
More in Agents
- 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.
- 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 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.
Written by Sume