Last refreshed 2026-06-07. Next refresh: weekly.
Why use Scribe v2 on ElevenLabs API?
ElevenLabs API offers Scribe v2 with competitive pricing. ElevenLabs' API provides hosted text-to-speech, speech-to-speech, dubbing, and voice models for creative production and realtime conversational applications.
Compare Scribe v2 across 2 providers to find the best fit for your use caseSetup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: scribe_v2scribe_v2Request example
scribe_v2.Gotchas
- Use provider model ID "scribe_v2", not the LLMReference slug "scribe-v2".
Compare Scribe v2 Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| ElevenLabs API | — | — |
| ElevenLabs API | — | — |
Capabilities
About Scribe v2
Scribe v2 is ElevenLabs' current state-of-the-art batch speech-to-text model, released January 12, 2026. Improvements over v1 for long-form audio, extended silences, and tone changes. Supports 90+ languages, word-level timestamps, 32-speaker diarization, 56 entity types, and keyterm prompting (up to 1,000 terms). Base pricing: $0.22/hr; entity detection add-on: $0.07/hr; keyterm prompting add-on: $0.05/hr. API ID: scribe_v2.
FAQ
What API model ID do I use for Scribe v2 on ElevenLabs API?
Use the model ID scribe_v2 when calling ElevenLabs API's API.
Who created Scribe v2?
Scribe v2 was created by ElevenLabs as part of the ElevenLabs Scribe model family.
Is Scribe v2 open source?
Scribe v2 is not open source; the seed data lists it as proprietary.