TikTok Symphony with Seedance 2.5: 30-second AI video ads
TikTok Symphony now generates up to 30 seconds with Seedance 2.5, in select markets. The same 30-second length is available by API on Sume as seedance-2.5.

TikTok's August 3 2026 post says Symphony, integrated with Dreamina Seedance 2.5, "now supports up to 30 seconds of video generation, up from a 15 second maximum before". It is rolling out to select advertisers in select markets. Outside that rollout, Sume's video API accepts seedance-2.5 at 4 to 30 seconds.
TikTok's details are from its Symphony announcement, read 2026-09-30. Sume's from the video generation docs.
Where is Symphony's 30-second option available?
Per TikTok, in the creation flow across Symphony Creative Studio and Symphony Automations in TikTok Ads Manager, for select paid advertisers in select markets. If your account is not in that group, you cannot use it there yet.
What does seedance-2.5 accept on Sume?
The docs state that seedance-2.5 accepts 4–30 seconds at 480p, 720p and 1080p, and that every other catalog model tops out at 15 seconds. The models endpoint lists accepted supported_input_references types per model, such as image_url, video_url and audio_url, and 9:16 is a valid aspect_ratio for vertical ads.
| Item | TikTok Symphony | Sume `seedance-2.5` |
|---|---|---|
| Max length | 30 seconds (was 15) | 30 seconds |
| Min length | Not stated | 4 seconds |
| Resolutions | Not stated | 480p, 720p, 1080p |
| Access | Select advertisers, select markets | Any API key |
How do I request a 30-second vertical clip?
Send model: "seedance-2.5", duration: 30 and aspect_ratio: "9:16" to the video endpoint, after checking the model's entry on the models endpoint. Reference-count limits are covered in Seedance 2.5 reference limits.
What if I need more than 30 seconds?
Join clips on a timeline; the steps are in 1-minute AI video generator.
Sources
Related posts
More in Models
- Vidu API: S2-Avatar live voice vs Sume avatar video jobs
Vidu S2-Avatar is a real-time voice model. Sume has no live session: you submit a script and a scene photo to an avatar job and fetch the finished video.
- Vidu S2-Editing: live stream edits vs a Sume Omni clip edit
Vidu S2-Editing edits an incoming video stream in real time. Sume edits one finished clip with a prompt through Gemini Omni video_to_video, as an async job.
- Wan 3.0 on Runway, or the wan-3.0 id as an API job on Sume
Runway's changelog lists Wan 3.0 in tool mode and workflows on paid plans. On Sume, wan-3.0 is a model id you call from code and poll as a job.
- An OpenRouter-compatible video API: sume/auto or a pinned model
Sume's POST /v1/videos follows OpenRouter's video generation API field for field. Let sume/auto pick the model, or pin a catalog id like seedance-2.5.
Written by Sume