ElevenLabsMicrosoftAudio matchupSpeech to text
Scribe v2vs.MAI-Transcribe-2
Which model is better?
Scribe v2 does better in independent tests.
Independent testsAppen MedTerm-90
Scribe v2ahead1 of 1
MAI-Transcribe-20 of 1
Popularityout of 100
Scribe v2ahead39
MAI-Transcribe-20
Weights and access
Scribe v2proprietary
MAI-Transcribe-2proprietary
Priceverbatim from the provider
Scribe v2n/a
MAI-Transcribe-2$0.10 per hour of audio as an introductory price
Pick Scribe v2 for
Appen MedTerm-90more popular
Pick MAI-Transcribe-2 for
No clear edge
Shared tests
Independent evaluators and leaderboards only, the newest shared snapshot per evaluator. With 95 % ranges a lead counts when they do not overlap; for hit rates, when it holds in a 95 % test. Without any uncertainty figure at most “slightly ahead”.
Appen MedTerm-90
Scribe v2 aheadAppen MedTerm-90 overall clinical entity recall
Scribe v283.4 %
MAI-Transcribe-281.3 %
95 % ranges 82.6 % to 84.1 % and 80.5 % to 82.1 %, 30,017 tasks, as of October 16, 2026
Source · latest October 16, 2026
All data side by side
Prices are verbatim from the provider, because audio models bill per minute, character or token.
| Scribe v2 | MAI-Transcribe-2 | |
|---|---|---|
| Task | Speech to text | Speech to text |
| Developer | ElevenLabs | Microsoft |
| Status | Active | Preview |
| Released | n/a | September 3, 2026 |
| Weights | proprietary | proprietary |
| Runs locally | no | no |
| Price | n/a | $0.10 per hour of audio as an introductory price |
| Popularity (out of 100) | 39 | 0 |