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
- Transcribe a 12-minute interview: 12 minutes costs $0.12 on Sume
Speech-to-text on Sume is $0.01 per audio minute, so a 12-minute interview (12 minutes) is $0.12. Video Inspect transcripts cost the same per minute.
- Transcribe a 90-minute lecture: 90 minutes costs $0.90 on Sume
Speech-to-text on Sume is $0.01 per audio minute, so a 90-minute lecture (90 minutes) is $0.90. Video Inspect transcripts cost the same per minute.
- Transcribe a 3-hour stream replay: 180 minutes costs $1.80 on Sume
Speech-to-text on Sume is $0.01 per audio minute, so a 3-hour stream replay (180 minutes) is $1.80. Video Inspect transcripts cost the same per minute.
- Transcribe a one-hour meeting: 60 minutes costs $0.60 on Sume
Speech-to-text on Sume is $0.01 per audio minute, so a one-hour meeting (60 minutes) is $0.60. Video Inspect transcripts cost the same per minute.
Written by Sume