Scribe v3
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
- Family
- ElevenLabs Scribe
- Released
- 2026-11-10
- Architecture
- Audio / Speech
- Specialization
- speech-recognition
- Openness
- Proprietary
- License
- ProprietaryRestricted
- Weights
- Not released
- Code
- Unknown
- Training
- Pretrained
Created by
Pricing
Audio / hour
$0.20 / hour of audio
Cheapest of 1 route · ElevenLabs API
Providers(1)
Links
Created by
Pricing
Audio / hour
$0.20 / hour of audio
Cheapest of 1 route · ElevenLabs API
Providers(1)
Links
About
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.
Providers(1)
Compare published audio / hour across 1 tracked provider route.
| Provider | Audio / hour | Route |
|---|---|---|
| ElevenLabs API | $0.20 / 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