# Scribe v3 (and Scribe v3 Live)

> ElevenLabs' third-generation speech-to-text pair, released 10 November 2026: Scribe v3 for recorded audio and Scribe v3 Live for realtime audio, with speaker labels on both.

- Maker: ElevenLabs
- Line: Scribe (speech-to-text)
- Canonical page: https://ai-tldr.dev/models/scribe-v3/
- Updated: 2026-11-10

## In short

Scribe v3 (and Scribe v3 Live) is an API-only model from ElevenLabs. ElevenLabs released it on 10 November 2026. You can use it through ElevenLabs API — Scribe v3 and ElevenLabs API — Scribe v3 Live.

## Facts

| Fact | Value | Source |
| --- | --- | --- |
| Input price | $0.20–$0.22 | [1] |
| Licence | Proprietary · API only | [2] |
| Released | 10 November 2026 | [3] |
| Parameters | Not disclosed | [2] |

## Sources

1. [ElevenLabs — API pricing](https://elevenlabs.io/pricing/api)
2. [ElevenLabs docs — Models](https://elevenlabs.io/docs/overview/models)
3. [ElevenLabs — Introducing Scribe v3 and v3 Live](https://elevenlabs.io/blog/scribe-v3)

## Overview

Scribe v3 is the pair of speech-to-text models ElevenLabs released on 10 November 2026: Scribe v3 (`scribe_v3`) transcribes recorded audio and Scribe v3 Live (`scribe_v3_live`) transcribes realtime audio. They succeed Scribe v2 and Scribe v2 Realtime, and ElevenLabs says upgrading takes only a model ID change. ElevenLabs' docs list both at 90+ languages, and both became the default in the ElevenLabs app.

For recorded audio, ElevenLabs reports 27% fewer word errors than Scribe v2 on FLEURS across 102 languages: average WER falls from 16.94% to 12.38%, and the docs say it improves on every language tested. Diarization handles up to 32 speakers, and ElevenLabs says it makes 12% fewer diarization errors than v2 overall and 17% fewer on recordings with three or more speakers. Other features are keyterm prompting with up to 1,000 terms, numbers as digits or words, secondary languages for mixed-language audio, entity detection, word-level timestamps, and exports to formats such as SRT, DOCX and PDF.

Scribe v3 Live is built for voice agents and live captioning. ElevenLabs reports 43% fewer errors than Scribe v2 Realtime, measured as semantic WER (an error counts only when the meaning changes), and 31% lower standard WER. It adds speaker diarization to the realtime model for the first time, plus turn prediction from conversation context so a caller who pauses mid-sentence is not cut off. It also adds a multilingual mode for mid-sentence language switches and a keyterm library of up to 10,000 terms. ElevenLabs' product page quotes under 150 ms latency, and a version tuned for medical conversations ships in ElevenAgents.

All of the comparisons are ElevenLabs' internal tests. FLEURS is a public benchmark, but the diarization results come from the company's own dataset of real meetings, agent calls and voice notes, which it says it will open-source. On its API pricing page, ElevenLabs lists batch transcription at $0.20 per hour of audio and realtime at $0.22 per hour.

## Pricing

- Input: $0.20–$0.22 / hour of audio

Scribe v3 (batch) $0.20 per hour; Scribe v3 Live (realtime) $0.22 per hour on the ElevenLabs API, with included hours on each plan.

Source: https://elevenlabs.io/pricing/api

## Strengths

- 27% fewer word errors than Scribe v2 on FLEURS across 102 languages (12.4% vs 17.0% WER), per ElevenLabs
- Lowest diarization error among the non-streaming models in ElevenLabs' test: 5.6% DER, against 6.4% for Scribe v2 and 8.5% to 14.2% for five other providers' models
- Scribe v3 Live reports 3.1% English diarization error against 5.9% to 7.3% for the other streaming models ElevenLabs tested
- Turn prediction from conversation context and a multilingual mode for mid-sentence language switches in the realtime model
- Keyterm prompting with up to 1,000 terms (batch) and a keyterm library of up to 10,000 terms (Live)
- Drop-in upgrade from Scribe v2: change the model ID and existing request parameters work unchanged

## Best for

- Reach for Scribe v3 for meeting, interview and podcast transcripts that need accurate speaker labels for up to 32 speakers.
- Reach for Scribe v3 Live as the listening stage of a voice agent, where turn prediction keeps a pausing caller from being cut off.
- Reach for keyterm prompting when audio is full of product names, postcodes or jargon that a general model would mishear.
- Reach for the multilingual mode for callers who switch language mid-sentence.

## How to access

- [ElevenLabs API — Scribe v3](https://elevenlabs.io/docs/overview/models) — model id `scribe_v3`
- [ElevenLabs API — Scribe v3 Live](https://elevenlabs.io/docs/overview/models) — model id `scribe_v3_live`

## Scribe (speech-to-text) versions

- Scribe v3 / Scribe v3 Live (10 November 2026): 27% fewer word errors than v2 on FLEURS; diarization added to the realtime model. — this page
- Scribe v2 / Scribe v2 Realtime: The previous batch and realtime Scribe models, which v3 succeeds with a model ID change.

## FAQ

### What is Scribe v3?

Scribe v3 is ElevenLabs' speech-to-text model for recorded audio, released on 10 November 2026 alongside Scribe v3 Live for realtime audio. Both are on the ElevenLabs API as `scribe_v3` and `scribe_v3_live`, and they succeed Scribe v2 and Scribe v2 Realtime.

### How much more accurate is Scribe v3 than Scribe v2?

On FLEURS across 102 languages, ElevenLabs reports 27% fewer word errors, with average WER falling from 16.94% to 12.38%. For Scribe v3 Live it reports 43% fewer errors than Scribe v2 Realtime on semantic WER and 31% lower standard WER. These are ElevenLabs' own tests.

### What does Scribe v3 cost?

ElevenLabs' API pricing page lists Scribe v3 at $0.20 per hour of audio and Scribe v3 Live at $0.22 per hour, with a number of included hours on each subscription plan.

### Does Scribe v3 Live label speakers?

Yes. Speaker diarization is new to the realtime model in v3. ElevenLabs reports a 3.1% diarization error rate on English recordings, against 5.9% to 7.3% for the other streaming models it tested. Draft speaker labels appear in partial transcripts.

### How do I upgrade from Scribe v2?

Change `model_id` from `scribe_v2` to `scribe_v3`; ElevenLabs says existing request parameters work unchanged. For Scribe v3 Live the default commit strategy is still `manual`, so turn prediction is used only once you set `commit_strategy` to `turn_prediction`.

### How many languages does Scribe v3 support?

ElevenLabs' docs list 90+ languages for both Scribe v3 and Scribe v3 Live. The headline FLEURS accuracy figures for Scribe v3 are averaged over all 102 FLEURS languages.

## Links

- [ElevenLabs — Introducing Scribe v3 and v3 Live](https://elevenlabs.io/blog/scribe-v3)
- [ElevenLabs docs — Models](https://elevenlabs.io/docs/overview/models)
- [ElevenLabs — API pricing](https://elevenlabs.io/pricing/api)
- [ElevenLabs — Speech-to-text API](https://elevenlabs.io/speech-to-text-api)

Source: AI/TLDR LLM registry, https://ai-tldr.dev/models/scribe-v3/