Key facts
- Provider
- ElevenLabs
- Model family
- Scribe
- Release date
- January 9, 2026
- Status
- Current
- Access
- API only
- API model id
- Not reported
- Context window
- Not reported
- Max output
- Not reported
- Input
- audio
- Output
- text
- Task families
- audio
- Declared capabilities
- speech to text, diarization, audio understanding
Scribe v2 pricing
Independent benchmark results
Scores come from independent evaluators that ran the model themselves, pinned to a dated snapshot. Rank is among current models in the same snapshot. ElevenLabs's own launch figures are listed under strengths with the publisher named, because they are not measured the same way.
No independent benchmark has published a result for Scribe v2 yet. It is still compared below on price, context and capabilities.
Strengths, cautions and best uses
Strengths
- ElevenLabs documents transcription in more than 90 languages with diarization
Cautions
- No exact compatible public benchmark snapshot is recorded
Best for
- Batch transcription and diarization
Alternatives to Scribe v2
The closest current audiomodels by price. The cheapest model that scores as well or better is listed first; failing that, the cheapest one within 3% of the benchmark's scale.
Gemini 3.1 Flash Live Preview
- From Google
Gemini 3.1 Flash TTS Preview
- From Google
GPT-Live 1
- From OpenAI
Qwen3.8-Omni-Flash
- From Alibaba Qwen
Other Scribe models
Scribe v2 FAQ
Is Scribe v2 open source or API only?
Scribe v2 is available through ElevenLabs's API only; its weights are not published.
What are the best alternatives to Scribe v2?
The closest current alternatives by price and measured performance are Gemini 3.1 Flash Live Preview (from Google), Gemini 3.1 Flash TTS Preview (from Google), GPT-Live 1 (from OpenAI) and Qwen3.8-Omni-Flash (from Alibaba Qwen).
Sources
- ElevenLabs models · ElevenLabs · official · verified August 10, 2026
- Introducing Scribe v2 · ElevenLabs · official · verified August 10, 2026
Cite this page
Van Data Team. "Scribe v2 Benchmarks, Pricing and Specs." AI Model Benchmark Dataset 2026-10-12. https://vandatateam.com/ai-model-benchmarks/scribe-v2
Reuse the data: JSON · CSV · or explore every model in the AI model benchmark comparison.
Production evaluation
Deciding whether Scribe v2 fits your workload?
Public benchmarks narrow the shortlist. We test the finalists on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.
- Evaluation cases and acceptance thresholds tied to real work
- Model routing, fallbacks and cost controls