audio model comparison
MAI-Transcribe-2-Streaming vs Scribe v2 Realtime
MAI-Transcribe-2-Streaming and Scribe v2 Realtime are both current audio models, from Microsoft AI and ElevenLabs. Scribe v2 Realtime is 28% cheaper per audio minute than MAI-Transcribe-2-Streaming, $0.0065 vs $0.009.
- Lower price per audio minute
- Scribe v2 Realtime$0.0065 against $0.009
- Newer release
- MAI-Transcribe-2-StreamingOct 2026 against Nov 2025
Data verified October 29, 2026 · Dataset 2026-10-29
Side by side
MAI-Transcribe-2-Streaming and Scribe v2 Realtime, line by line
Prices in effect today, compared at the same tier wherever both list one. The better value in each row is highlighted.
| Fact | MAI-Transcribe-2-Streaming | Scribe v2 Realtime |
|---|---|---|
| Price | ||
| Price per audio minute | $0.009 | $0.0065 (better) |
| Independent benchmarks | ||
| Artificial Analysis AA-WER Streaming | Not measured | 3.59 % WER (#2 of 2) |
| Specs | ||
| Provider | Microsoft AI | ElevenLabs |
| Release date | October 1, 2026 | November 11, 2025 |
| Access | API only | API only |
| Context window | Not reported | Not reported |
| Max output | Not reported | Not reported |
| Input | audio | audio |
| Output | text | text |
No independent benchmark has scored both models yet. Each rank counts the current models scored on that benchmark.
Charts
Against every current audio model
Where MAI-Transcribe-2-Streaming and Scribe v2 Realtime land among the current models of their task, on every independent benchmark, on price and on context.
Where each stands
No independent benchmark has scored either model yet, so the tiles rank their prices among the current models of their task.
Price and context
Price per audio minute
MAI-Transcribe-2-Streaming:#11of 14
$0.009 · cheaper than 15%
Scribe v2 Realtime:#10of 14
$0.0065 · cheaper than 31%
Cost
What each costs
Example workloads at each provider's listed rates, then every other rate either one lists. The cheaper figure in each row is highlighted.
The same work, priced
For 100 hours of audio, MAI-Transcribe-2-Streaming costs 1.4 times as much as Scribe v2 Realtime, at each provider's listed rates.
100 hours of audio
MAI-Transcribe-2-Streaming costs 1.4× as much
- MAI-Transcribe-2-Streaming
- $54
- Scribe v2 Realtime
- $39
| Workload or rate | MAI-Transcribe-2-Streaming | Scribe v2 Realtime |
|---|---|---|
| Example workloads | ||
| 100 hours of audio | $54 | $39 (better) |
Verdict
When to choose each
MAI-Transcribe-2-Streaming
Where it leads
No measured lead over Scribe v2 Realtime in this data.
Best for
- Live captions and voice agents
- Multilingual calls where speakers switch languages
Watch out for
- Microsoft Foundry lists it as a preview
- The $0.54 per hour price is introductory until the end of 2026, and the later price is not published
Scribe v2 Realtime
Where it leads
- Lower price per audio minute, $0.0065 vs $0.009
- Supports realtime voice and audio understanding
Best for
- Live transcription
Watch out for
- $0.39 per hour of audio, about 1.8 times batch Scribe v2
From benchmark to production
Building on MAI-Transcribe-2-Streaming or Scribe v2 Realtime?
Public scores rarely hold on your own data. We test both models on your real tasks, then build the agent or pipeline around the one that wins.
FAQ
MAI-Transcribe-2-Streaming vs Scribe v2 Realtime FAQ
Which is cheaper, MAI-Transcribe-2-Streaming or Scribe v2 Realtime?
Scribe v2 Realtime is 28% cheaper per audio minute than MAI-Transcribe-2-Streaming, $0.0065 vs $0.009.
How much would 100 hours of audio cost with MAI-Transcribe-2-Streaming or Scribe v2 Realtime?
100 hours of audio comes to $54 with MAI-Transcribe-2-Streaming and $39 with Scribe v2 Realtime at their listed rates.
How do MAI-Transcribe-2-Streaming and Scribe v2 Realtime differ in features?
Only Scribe v2 Realtime supports realtime voice and audio understanding.
Further reading
More on MAI-Transcribe-2-Streaming and Scribe v2 Realtime
Related comparisons
- Gemini 3.5 Transcribe vs MAI-Transcribe-2-Streaming
- Grok Voice Transcribe 2.0 vs Scribe v2 Realtime
- GPT-4o Transcribe vs MAI-Transcribe-2-Streaming
- Gemini 3.8 Live vs Scribe v2 Realtime
- GPT Transcribe vs MAI-Transcribe-2-Streaming
- Gemini 3.5 Transcribe vs Scribe v2 Realtime
- MAI-Transcribe-2 vs MAI-Transcribe-2-Streaming
- GPT Transcribe vs Scribe v2 Realtime
- Gemini 3.1 Flash Live Preview vs Scribe v2 Realtime
- Scribe v2 vs Scribe v2 Realtime
- Gemini 3.5 Live Translate Preview vs Scribe v2 Realtime
- GPT-4o Transcribe vs Scribe v2 Realtime
Production evaluation
Choosing between MAI-Transcribe-2-Streaming and Scribe v2 Realtime?
Public benchmarks narrow the shortlist. We run both on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.
- A head-to-head evaluation on your real workload
- Routing between models by cost and difficulty