Fact · Languages and accents
90languages
ElevenLabs' speech-to-text documentation says its Scribe v2 model supports 90 or more languages, and lists them with their codes.
Quote found word for word on the live source, last checked October 19, 2026
In the source's own words
“Scribe v2 supports 90+ languages, including: Afrikaans (afr), Amharic (amh), Arabic (ara)”
Speech to Text (ElevenLabs documentation), ElevenLabs, 2026, Speech to Text, Supported languages section.
Open the original- What it measures
- ElevenLabs' documentation page for its speech-to-text API. The page gives the same 90+ figure for Scribe v2 Realtime.
- What it does not show
- 90+ is a floor stated by ElevenLabs, not an exact total, and the page lists the languages only in part. The page says ElevenLabs keeps adding languages.
In the data
A row of How Many Languages Speech Recognition Supports, as ElevenLabs Scribe v2: 90 languages.
- System
- ElevenLabs Scribe v2
- Maker
- ElevenLabs
- Kind
- Cloud speech API
- What is counted
- Languages
- On device
- Not stated
- As of
- 2026-10
- Note
- The page says 90+ languages, so 90 is the stated floor and the true count may be higher.
Source
Used to calculate
- In the languages supported by speech recognition systems dataset, the 10 published figures for “Cloud speech API” have a median of 94 languages, ranging from 13 to 125.
- The languages supported by speech recognition systems dataset holds 45 data points, each a published figure traced to its source.
- The languages supported by speech recognition systems dataset draws on 39 distinct sources.