12-minute interview: two STT jobs, detach ranges 0-600 and 600-720
Sume STT takes up to 10 minutes per job. Detach a 12-minute interview in two ranges, 0 to 600 and 600 to 720 seconds, and transcribe both for about 14 cents.
A 12-minute interview does not fit one Sume STT job, which accepts a duration_seconds hint of 1 to 600. Detach the audio as two ranges, 0 to 600 and 600 to 720 seconds, then send each file to POST /v1/stt-1.0/transcribe. At $0.01 per audio minute plus two $0.01 detach jobs, that is about $0.14.
Limits are from the Audio detach docs and the STT 1.0 request in the Sume API reference (read 2026-10-06).
How do I cut the audio?
POST /v1/audio-detach takes one workspace video on media.sume.com and an optional range of { start, end } seconds. The docs name sample_rate: 16000 with channels: "mono" as the STT shape. The output is capped at 900 seconds, so each of these ranges fits. A source with no audio fails with detach_source_has_no_audio.
What does it cost?
STT is priced at $0.01 per audio minute (a $0.008 list rate with the standard 1.25 margin), and each detach is $0.01 per job. Send duration_seconds so the reservation matches the chunk, or Sume reserves one minute.
| Step | Count | Rate | Total |
|---|---|---|---|
| Audio detach | 2 jobs | $0.01 per job | $0.02 |
| STT, 0 to 600 s | 10 minutes | $0.01 per minute | $0.10 |
| STT, 600 to 720 s | 2 minutes | $0.01 per minute | $0.02 |
| All | $0.14 |
How do I join the transcripts?
Each result has words[] with times counted from the start of its own chunk. Add 600 to every time in the second transcript before you merge them. A word split across the 600-second cut can be cut in half, so move the boundary to a pause if the speech is continuous.
Sources
More in Media tools
- A 15-second Reel at 128 BPM is eight bars: put tempo in the prompt
At 128 BPM in 4/4, eight bars last exactly 15 seconds. Write the BPM and a named moment into the Sume music prompt, then check the audio: BPM is a direction.
- 16:9 insert in a 1080x1920 Short: Timeline fit modes compared
In a 1080x1920 Timeline, cover keeps 31.6% of a 16:9 clip's width, contain shrinks it to 608 px tall, stretch distorts it and blur pads it.
- 45-minute webinar into YouTube Shorts: Sume trim takes 30 minutes
Sume video trim accepts a source up to 1800 seconds and cuts up to 900. A 45-minute webinar needs a split first; YouTube Shorts run up to 3 minutes.
- 720p landscape to a TikTok 9:16 ad: a 405-wide crop misses 540x960
Cropping 16:9 to 9:16 keeps 31.6% of the width. A 1080p source gives about 608x1080 and clears TikTok's 540x960 minimum; 720p gives 405x720 and does not.
Written by Sume