Scribe v3 Live

Released
2026-11-10
Last refreshed
2026-11-11
Status
Researched 1d ago
ProprietaryCommercial use: restricted
ElevenLabs releases · 7 in the last 12 months · this family litChangelog →
Specifications
Released
2026-11-10
Architecture
Audio / Speech
Specialization
speech-recognition
Openness
Proprietary
License
ProprietaryRestricted
Weights
Not released
Code
Unknown
Training
Pretrained
Created by

AI audio research and text-to-speech platform.

New York, New York, United States
Founded 2022
Website
Pricing
Audio / hour
$0.22 / hour of audio

Cheapest of 1 route · ElevenLabs API

Providers(1)

About

Scribe v3 Live is ElevenLabs' real-time speech-to-text model with turn prediction, released November 10, 2026 as the successor to Scribe v2 Realtime. ElevenLabs reports improved turn detection, a keyterm library and multilingual mode across 90+ languages, and it is also available in ElevenAgents. API pricing is $0.22 per hour of audio.

Providers(1)

Compare published audio / hour across 1 tracked provider route.

ProviderAudio / hourRoute
ElevenLabs API$0.22 / hour of audio
Serverless

Capabilities

Audio

Benchmark peer barsfor Coding

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

API versions

scribe_v3_live