Fact · Languages and accents
43languages
DeepL's Voice API documentation lists transcription for 43 languages, counting each pair of regional variants, such as English (American) and English (British), as one language.
Quote found word for word on the live source, last checked October 20, 2026
In the source's own words
“**Language** | **Transcription** | **Translation** | **Translated Speech** ... Arabic | ⎋ | ✓ | ⎋ ... Vietnamese | ⎋ | ✓ | ⎋”
Supported Voice Languages, DeepL, DeepL, developer documentation for the Voice API, n.d., Supported Voice Languages table.
Open the original- What it measures
- The table has 48 entries and gives a transcription mark on every row. Regional variants such as English (American) and English (British) are separate entries. Counting five pairs of variants (Chinese, English, French, Portuguese and Spanish) as one language each leaves 43 languages. The quote shows the header, the first row and the last row, and the count covers every row. DeepL transcribes 18 of the 43 languages itself, and an external service partner provides transcription for the other 25. Translation is always provided by DeepL.
- What it does not show
- The page states no total, so 43 is counted from its table. Partner transcription cannot yet detect the source language automatically, so the speaker must set the language. The list is for the Voice API, and the Voice for Meetings support article gives different approximate groupings that were not checked here.
In the data
A row of How Many Languages Speech Recognition Supports, as DeepL Voice, transcription: 43 languages.
- System
- DeepL Voice
- Maker
- DeepL
- Kind
- Cloud speech API
- What is counted
- Languages
- On device
- Not stated
- As of
- 2026-10
- Note
- Counted from the table: 48 entries, with five pairs of regional variants counted as one language each (Chinese, English, French, Portuguese, Spanish), gives 43 languages. The page states no total.
Source
Used to calculate
- In the languages supported by speech recognition systems dataset, the 48 published figures for “Cloud speech API” have a median of 46 languages, ranging from 1 to 204.
- The languages supported by speech recognition systems dataset holds 207 data points, each a published figure traced to its source.
- The languages supported by speech recognition systems dataset draws on 172 distinct sources.