LLM Reference

ElevenLabs Scribe Models by ElevenLabs

ElevenLabsProprietaryProprietary
3 models2025–2026

Details

ResearcherElevenLabs
LicenseProprietary
Commercial useCommercial use with conditions
Models3
Released2025–2026

Links

Website

About

ElevenLabs' speech-to-text (Scribe) model family. Scribe v2 (January 2026) supports 90+ languages, 32-speaker diarization, 56 entity types, and keyterm prompting. Scribe v2 Realtime (~150ms) is optimized for voice agents. Scribe v1 is deprecated — migrate to v2.

Current Variants

Use-when guidance is derived from seed capabilities, context, release, and replacement fields.

2 in view1 retired
Scribe v2Current

Use when the workload needs transcription and audio.

2026-01transcriptionaudio

Use when the workload needs transcription and audio.

2025-11transcriptionaudio

Release Timeline

3 release groups
2026-01
1 current
Scribe v2
transcriptionaudio
Current
2025-11
1 current
Scribe v2 Realtime
transcriptionaudio
Current
2025-02
1 retired
Scribe v1
transcriptionaudio
Archived

Specifications(3 models)

ElevenLabs Scribe model specifications comparison
ModelReleased
Scribe v22026-01
Scribe v2 Realtime2025-11

Available From(1 provider)

Frequently Asked Questions

What is ElevenLabs Scribe used for?
ElevenLabs Scribe is used for transcription and agent workflows. The family description and listed model capabilities point to those workloads as the best fit.
How does ElevenLabs Scribe compare to ElevenLabs Text-to-Speech?
ElevenLabs Scribe by ElevenLabs is strongest where you need transcription, while ElevenLabs Text-to-Speech by ElevenLabs is the closest related family to check for audio. ElevenLabs Scribe has 3 listed variants, so compare the specs and pricing tables before choosing a production model.
Which ElevenLabs Scribe model should I use?
If price is the main constraint, use the pricing table first because ElevenLabs Scribe does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate Scribe v2.