audio model comparison
Scribe v2 Realtime vs Scribe v3
Scribe v2 Realtime and Scribe v3 are both current audio models, from ElevenLabs. Scribe v3 is 9% cheaper per audio minute than Scribe v2 Realtime, $0.003333 vs $0.003667.
- Lower price per audio minute
- Scribe v3$0.003333 against $0.003667
- Newer release
- Scribe v3Nov 2026 against Nov 2025
Data verified November 15, 2026 · Dataset 2026-11-15
Side by side
Scribe v2 Realtime and Scribe v3, 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 | Scribe v2 Realtime | Scribe v3 |
|---|---|---|
| Price | ||
| Price per audio minute | $0.003667 | $0.003333 (better) |
| Independent benchmarks | ||
| Artificial Analysis AA-WER Streaming | 3.59 % WER (#4 of 4) | Not measured |
| Artificial Analysis AA-WER v2 | Not measured | 1.95 % WER (#1 of 8) |
| Specs | ||
| Provider | ElevenLabs | ElevenLabs |
| Release date | November 11, 2025 | November 10, 2026 |
| 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.
Scores:Artificial Analysis · 2026-11-15Artificial Analysis · 2026-11-15
Charts
Against every current audio model
Where Scribe v2 Realtime and Scribe v3 land among the current models of their task, on every independent benchmark, on price and on context.
Where each stands
Only Scribe v3 has a current Artificial Analysis AA-WER v2 score: #1 of 8. Each bar is the share of current models it beats.
Independent benchmarks
Artificial Analysis AA-WER v2
Scribe v2 Realtime: Not scored
Scribe v3:#1of 8
1.95% WER · ahead of 100%
Artificial Analysis AA-WER Streaming
Scribe v2 Realtime:#4of 4
3.59% WER · ahead of 0%
Scribe v3: Not scored
Price and context
Price per audio minute
Scribe v2 Realtime:#5of 16
$0.003667 · cheaper than 67%
Scribe v3:#3of 16
$0.003333 · cheaper than 80%
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, Scribe v2 Realtime costs 1.1 times as much as Scribe v3, at each provider's listed rates.
100 hours of audio
Scribe v2 Realtime costs 1.1× as much
- Scribe v2 Realtime
- $22
- Scribe v3
- $20
| Workload or rate | Scribe v2 Realtime | Scribe v3 |
|---|---|---|
| Example workloads | ||
| 100 hours of audio | $22 | $20 (better) |
Your own bill will differ. These figures use list prices and example workloads. The AI Model Cost Audit reviews your real usage, shortlists models that score as well for each task for less, and estimates the savings.
Launch price $100, regular price $150
Verdict
When to choose each
Scribe v2 Realtime
Where it leads
- Supports realtime voice
Best for
- Live transcription
Watch out for
- $0.22 per hour of audio, $0.02 more than batch Scribe v2
- ElevenLabs followed it with Scribe v3 Live on November 10, 2026, at the same price and with speaker diarization; Artificial Analysis measures 2.86% for v3 Live against 3.59% for v2 Realtime on AA-WER Streaming
Scribe v3
Where it leads
- Lower price per audio minute, $0.003333 vs $0.003667
- Supports speaker diarization
Best for
- Accurate batch transcription of meetings, calls and archives in many languages
- Transcripts that need reliable speaker labels
Watch out for
- Keyterm prompting and transcript editing cost extra: $0.05 and $0.07 per hour of audio
- ElevenLabs' comparisons use its own internal version of FLEURS and a meeting and call dataset it has not published yet
- Built for recorded audio: live transcription is the separate Scribe v3 Live model, at $0.22 per hour
From benchmark to production
Building on Scribe v2 Realtime or Scribe v3?
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.
AI Model Cost AuditLaunch price $100, regular price $150
FAQ
Scribe v2 Realtime vs Scribe v3 FAQ
Which is cheaper, Scribe v2 Realtime or Scribe v3?
Scribe v3 is 9% cheaper per audio minute than Scribe v2 Realtime, $0.003333 vs $0.003667.
How much would 100 hours of audio cost with Scribe v2 Realtime or Scribe v3?
100 hours of audio comes to $22 with Scribe v2 Realtime and $20 with Scribe v3 at their listed rates.
How do Scribe v2 Realtime and Scribe v3 differ in features?
Only Scribe v2 Realtime supports realtime voice. Only Scribe v3 supports speaker diarization.
AI Model Brief
The AI models worth knowing, once a week
What shipped, how it scores on independent benchmarks, what it costs per million tokens and what was deprecated, from the data behind our AI model benchmarks.
We use your address only to send the brief. See our privacy policy.
See this week’s briefFurther reading
More on Scribe v2 Realtime and Scribe v3
Related comparisons
- Scribe v2 Realtime vs Scribe v3 Live
- Scribe v2 vs Scribe v3
- MAI-Transcribe-2-Streaming vs Scribe v2 Realtime
- Scribe v3 vs Scribe v3 Live
- Grok Voice Transcribe 2.0 vs Scribe v2 Realtime
- Gemini 3.8 Live vs Scribe v2 Realtime
- Gemini 3.5 Transcribe vs Scribe v2 Realtime
- 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 Scribe v2 Realtime and Scribe v3?
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