gpt-realtime-translate pricing: $0.034 per minute, and STT plus TTS
OpenAI lists gpt-realtime-translate at $0.034 per minute. Sume has no live translate line; STT 1.0 and TTS 1.0 are separate rates you add up yourself.
OpenAI's pricing page lists gpt-realtime-translate ("Live translation") at $0.034 per minute. Sume does not list a single live-translate rate in the sources cited here. Two of its lines apply to a spoken-in, spoken-out pipeline: STT 1.0 at $0.01 per audio minute and TTS 1.0 at $0.0475 per 1,000 characters.
Read 2026-10-01. The sum below leaves out any translation step between the two, because no rate for one is cited here.
What does one minute of speech add up to on Sume?
STT is priced per audio minute and TTS per 1,000 characters, so the units differ. As an illustration only, take one minute of audio and a 1,000-character script (how many characters a minute of speech holds depends on the language and pace).
| Line | Rate | Amount in the example |
|---|---|---|
| Sume STT 1.0 | $0.01 per audio minute | $0.01 |
| Sume TTS 1.0 | $0.0475 per 1,000 characters | $0.0475 |
| Sum of the two | - | $0.0575 |
OpenAI gpt-realtime-translate | $0.034 / minute | $0.034 |
What limits apply to the two lines?
STT reserves 1 minute when no duration is given, with a minimum of 1 second and a maximum of 10 minutes. TTS counts spaces and punctuation toward the character total, and the catalog's maximum estimate is built on 20,000 characters.
Is this a live translator?
No. These are jobs on files and text, reserved and captured per Generation admission. If you need to dub a recorded video, the pipeline is in build an AI dubbing pipeline and translate a video voiceover.
Where do I check the live Sume rates?
The Usage docs say the API pricing page is generated from the same constants the API bills on; check it before budgeting.
Sources
Related posts
More in Pricing
- Is Runway free? 125 one-time credits, and Sume's Free plan
Runway has a $0 Free plan with 125 one-time credits; Standard is $15 per month. Sume's Free plan covers image generation with no card and 1 concurrent job.
- Kling 3.0 4K on Luma: 147 credits per second, audio on or off
Luma lists Kling 3.0 at 2160p for 147 credits per second with or without audio; at 1080p it is 40 without and 49 with. Sume has a generate_audio field.
- MiniMax H3 Max on Luma: credits per second in dollars
Luma lists MiniMax H3 Max at 18, 28 and 56 credits per second. Here is that in dollars by plan, and the per-second dollar rate Sume bills instead.
- Veo 3.1 on Luma with audio: 280 credits per second, double 140
Luma lists Veo 3.1 at 140 credits per second without audio and 280 with, at 720p and 1080p. Google lists dollars per second. Sume has a generate_audio field.
Written by Sume