ElevenLabs Scribe v2 pricing: $0.22/hour plus add-ons

ElevenLabs lists Scribe v2 at $0.22 per hour. Entity detection ($0.070 per hour) and keyterm prompting ($0.050 per hour) are separate lines, so one hour with both add-ons comes to $0.34. Sume STT 1.0 is priced per audio minute: $0.01 per minute, or $0.60 for an hour.

Vendor numbers are as written on the ElevenLabs API pricing page, read 2026-09-30. Sume's rate is from the Video inspect docs.

How much does one hour of Scribe v2 cost with add-ons?

Add the lines you turn on. The table uses only the three per-hour figures from the pricing page.

How do I budget for my own hours?

Multiply the row you need by the audio hours you expect per month. For 40 hours with both add-ons that is 40 x $0.34 = $13.60.

What is the Sume STT 1.0 price for the same hour?

Sume STT 1.0 has one rate per audio minute. Sixty minutes is 60 x $0.01 = $0.60. The docs list no entity-detection or keyterm line for it, so there is nothing to add on top. Completed results return text and words[] word-level timings. This is a price comparison of numbers only; it says nothing about accuracy or feature parity.

What limits apply to a Sume STT request?

Omit duration_seconds and Sume reserves one minute; the maximum is 10 minutes per request. For an hour of audio, split it into chunks of at most 10 minutes; see transcribe long audio files.