Apple Podcasts host-read video ads: cut the spot with Sume trim
Apple Podcasts lets creators insert video ads including host-read spots. Cut a host-read spot from an episode with Sume's exact-precision video trim.

Apple says its new video podcast experience lets creators dynamically insert video ads, including host-read spots (read 2026-10-02). If your host-read ad is recorded inside a full episode, cut it out as its own file with Sume's video trim using precision: "exact". Sume does not insert ads or deliver to Apple, and Apple's announcement does not give file specs for ad insertion.
What Apple announced
Apple's newsroom post describes video podcasts delivered with HLS in Apple Podcasts. The facts below are as the page states them.
| Item | What the page says |
|---|---|
| Delivery | HLS video |
| Ads | Creators can dynamically insert video ads, including host-read spots |
| Beta | iOS 26.4 |
| Full rollout | Spring 2026 |
| Ad-network fee | Impression-based, starting later in 2026 |
Cutting the spot
Find the spot's start and end times in the episode, for example from the sentence segments that video inspect returns with transcribe: true. Then call POST /v1/video-trim with start and duration or end, and an Idempotency-Key. Source video must be in your workspace on media.sume.com and at most 1800 seconds, so a longer episode needs splitting first.
Why exact precision
exact is the default and re-encodes so the cut starts on the frame you asked for. keyframe is a stream copy that can start one GOP early, which for an ad can leave a fragment of the previous sentence at the start. If you use it, read actual_start_seconds from the result to see where the cut really began.
- Cut from the first word of the ad to the last, with a short margin if you want one.
- Keep
audioatkeep; a host-read ad is the voice. - Listen to both ends of the output before you hand it over.
What stays outside Sume
Ad insertion, the ad network and the delivery format are Apple's. Check Apple's Podcasts documentation for what an ad file must be, because the announcement does not say. Sume only prepares a clean cut of the video you already have.
Sources
Related posts
More in Use cases
- AI Act marking exemption for B2B and industrial output: how narrow
The Commission FAQ says a narrow Article 50(2) marking exemption is envisaged for B2B or industrial outputs, with conditions in the guidelines. What it lists.
- AI Act Article 50 fines: up to EUR 15M or 3%, and who enforces it
The Commission's Article 50 FAQ says fines can reach 15 million euros or 3% of worldwide turnover, enforced mainly by national market surveillance authorities.
- AI Act Article 50 for non-EU providers: output used in the EU
The Commission FAQ says providers outside the EU are subject to the AI Act if their system's output is used in the EU. How it defines provider and deployer.
- Can one avatar UGC ad change location mid-video? One scene only
Sume's avatar video renders one avatar and one shared scene per final video. For a second location, make two jobs and join them with a Timeline 1.0 render.
Written by Sume