Transcribing a 3-minute Short: 3 cents, and the 600-second hint cap
Sume video inspect transcribes at $0.01 per audio minute. A 180-second Short is 3 cents with duration_seconds set, and 1 minute is reserved if you omit it.
A 3-minute Short costs 3 cents to transcribe with Sume video inspect: the public rate is $0.01 per audio minute, and duration_seconds: 180 tells Sume to reserve exactly 3 minutes. If you leave the hint out, Sume reserves 1 minute, and the hint tops out at 600 seconds, so anything longer than 10 minutes needs a cut first.
These figures come from the video inspect docs (read 2026-10-06). The Short's own limit is 3 minutes per YouTube Help.
What changes the transcript price?
The figures are laid out below.
| Setting | Effect | Example |
|---|---|---|
transcribe: true | Runs Sume STT 1.0 on the clip's audio | Required for all STT fields |
duration_seconds | Reserve for that many seconds, maximum 600 | 180 gives 3 minutes, $0.03 |
| No hint | Reserves 1 minute | A 3-minute clip may need more |
segmentation.mode: sentence | Also returns gapless sentence segments[] | Caption-shaped lines |
What errors should I expect?
Sending language_code, segmentation, or duration_seconds without transcribe: true returns 400 video_inspect_transcribe_required. A clip with no audio track returns inspect_source_has_no_audio; check probe.has_audio first with frames: false. The default mode is sync and waits up to 30 seconds before returning 202 with a job to poll.
When is it worth it for a Short?
A transcript lets you check the hook in the first sentence, write the title, and place caption cues at sentence ends. At 3 cents for a full-length Short, it costs less than a single caption job ($0.20 for a clip up to 60 seconds), and it gives you words rather than burned pixels. Confirm the live rate in GET /v1/catalog before budgeting a season.
Sources
Related posts
More in Pricing
- Trim first, then caption: the 60-second note on the caption price
Sume quotes the $0.20 video-captions price for videos up to 60 seconds. Cut the episode with video trim at $0.02 first, then caption only the part you keep.
- 10,000-character TTS script: one 48-cent job or three chunks?
A 10,000-character script costs 48 cents on Sume TTS as one job. Splitting into three adds at most a cent or two of rounding, so chunk only for a reason.
- Upgrading Sume Pro to Scale mid-month: what happens to unused usage
An upgrade starts a new billing cycle now and grants the new plan's full included usage. Unused usage from the old plan is superseded, not added.
- Veo 3.1 draft ladder: five Lite takes then one Standard final, $5.20
Five 8-second Lite drafts and one Standard 1080p final cost $5.20 at Google's list prices. Six Standard takes cost $19.20. Prices read 2026-10-06.
Written by Sume