Transcription cost on Sume STT, by audio length
Sume STT 1.0 bills per audio minute, so a transcript costs that rate times the minutes. The cost of interviews, webinars, workshops and stream replays.
Sume STT 1.0 bills transcription per audio minute, and the Video Inspect transcript is priced at the same per-minute rate, so a transcript's cost is that rate times the length of the recording. The table gives it for every recording these posts priced.
Worked example: Transcribe a 3-hour stream replay: 180 minutes costs $1.80 on Sume
Transcribing a 3-hour stream replay takes 180 audio minutes and costs $1.80 on Sume. The Sume STT 1.0 rate is $0.01 per audio minute after margin on a $0.008 provider list price, and the Video Inspect transcript SKU is priced at $0.01 per minute too.
Sume's video inspect docs (read 2026-10-06) say the default mode is sync and the handler waits at most 30 seconds, so for anything this long ask for async and poll the job.
What does a batch of these cost?
The price is linear in audio minutes.
| Files | Minutes each | Total minutes | Total |
|---|---|---|---|
| 1 | 180 | 180 | $1.80 |
| 4 | 180 | 720 | $7.20 |
| 20 | 180 | 3600 | $36.00 |
What should I plan for?
The estimate is for the transcript alone; captions, trims and renders are separate jobs.
- Long recordings run async: submit, then poll
GET /v1/jobs/{id}/resultor take a webhook. - The price is by audio minutes, not by words, so silence costs the same as speech.
- Check the live price in
GET /v1/catalog(sume/stt-1.0).
Every recording length in one table
This page replaces 8 posts that asked the same question with different numbers. Each row is one of them, with the answer it gave when it was published.
| Question | Answer |
|---|---|
| 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 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 two-hour workshop: 120 minutes costs $1.20 on Sume | Speech-to-text on Sume is $0.01 per audio minute, so a two-hour workshop (120 minutes) is $1.20. Video Inspect transcripts cost the same per minute. |
| Transcribe a 25-minute webinar clip: 25 minutes costs $0.25 on Sume | Speech-to-text on Sume is $0.01 per audio minute, so a 25-minute webinar clip (25 minutes) is $0.25. Video Inspect transcripts cost the same per minute. |
| Transcribe a 5-minute voice memo: 5 minutes costs $0.05 on Sume | Speech-to-text on Sume is $0.01 per audio minute, so a 5-minute voice memo (5 minutes) is $0.05. 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 45-minute podcast episode: 45 minutes costs $0.45 on Sume | Speech-to-text on Sume is $0.01 per audio minute, so a 45-minute podcast episode (45 minutes) is $0.45. 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. |
Sources
Related posts
More in Pricing
- Veo 3.1 at Google's list price vs the cheapest Sume row
Google's list price for a Veo 3.1, Veo 3.1 Fast or Veo 3.1 Lite clip next to the cheapest Sume row that makes the same length and resolution. Price only.
- Wan 3.0 cost for sets of short ad clips on Sume, vs Omni Flash
What a set of short ad clips costs on Sume with Wan 3.0 at 480p, 720p and 1080p, next to Gemini Omni Flash 1.1, for every set and length these posts priced.
- What an AI video budget buys on Sume: seconds and length by model
How many seconds of video a budget buys on each Sume model, and the longest clip each model makes under a per-clip price ceiling, at 720p and 1080p.
- AI avatar video API pricing: cost per second and per minute
Sume bills AI avatar video per second by quality tier, with separate rates when you send a product image. Per-minute costs for standard, plus, and max.
Written by Sume