Scribe v2
Scribe v2 is ElevenLabs' documented state-of-the-art speech recognition model. The model ID is scribe_v2.
Provider
ElevenLabs
Model family
ElevenLabs
Speech-to-text
Cost tier
Scribe
Status
Current
Why teams choose it
Complex reasoning
Useful for workflows that require structured thinking, multi-step logic, and deeper analysis than lightweight models provide.
Long-context analysis
Helps teams summarize, compare, and extract insights from long documents without losing important nuance.
ElevenLabs roadmap vigilance
Use published model pages—not stale marketing blurbs—for modalities, quotas, pricing, and policy; schedule revalidation tied to vendor release notes.
Cost-efficient routing
Useful as part of a routing stack where cheap models handle drafts and confirmations and this tier handles genuinely hard passages.
Tradeoffs to know
- No dollar rate is published on the models overview.
Technical specs
- Inputs
- audio
- Outputs
- text
- Capabilities
- speech to text, 90+ languages
- License
- Proprietary API
- API ID
scribe_v2- Source
- https://elevenlabs.io/docs/overview/models
- Languages
- 90+
- Realtime Api Id
- scribe_v2_realtime
Benchmarks
No independent or vendor benchmark scores in this catalog entry.
ElevenLabs family lineup
Related models
Scribe v2 FAQ
What is Scribe v2?
Scribe v2 is ElevenLabs' documented state-of-the-art speech recognition model. The model ID is scribe_v2. It supports 90+ languages. The realtime sibling on the same models page is scribe_v2_realtime. Scribe v1 is listed as outclassed by the v2 models.
When does Scribe v2 fit best?
Multilingual speech recognition
What should teams watch out for with Scribe v2?
No dollar rate is published on the models overview.
Explore next
Models, tools, and comparisons that connect to this reference.