Last refreshed 2026-11-11. Next refresh: weekly.
Why use Scribe v3 on ElevenLabs API?
ElevenLabs API offers Scribe v3 with pay-as-you-go pricing at $0.20 / hour of audio. ElevenLabs' API provides hosted text-to-speech, speech-to-speech, dubbing, and voice models for creative production and realtime conversational applications.
Audio / hour
$0.20 / hour of audio
Output / 1M
-
Cache
Not sourced
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: scribe_v3Model ID
scribe_v3Request example
Curated snippets for this provider are not sourced yet. Use ElevenLabs API documentation with model ID
scribe_v3.Gotchas
- Use provider model ID "scribe_v3", not the LLMReference slug "scribe-v3".
Pricing
| Type | Rate |
|---|---|
| Audio hour | $0.20 / hour of audio |
Capabilities
Audio
About Scribe v3
Scribe v3 is ElevenLabs' batch speech-to-text model for recorded audio, released November 10, 2026 as the successor to Scribe v2. ElevenLabs calls it its most accurate speech recognition model, with number formatting and language hints across 90+ languages. API pricing is $0.20 per hour of audio.
Get Started
Model Specs
Released2026-11-10
ArchitectureAudio / Speech