Fact · Languages and accents
48language entries
DeepL's Voice API documentation lists 48 language and regional variant entries for transcription, each with a transcription mark.
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 one row per language or regional variant, such as Chinese (simplified) and Chinese (traditional), or English (American) and English (British). Every row has a transcription mark, either DeepL's own or an external partner's. The 43-language count in the companion fact merges the regional variants. The quote shows the header, the first row and the last row, and the count covers every row.
- What it does not show
- This is a count of table rows, not a language count. The page states no total. Use the 43-language figure when the question is how many languages are recognized.
In the data
A row of How Many Languages Speech Recognition Supports, as DeepL Voice, incl. regional variants: 48 languages.
- System
- DeepL Voice
- Maker
- DeepL
- Kind
- Cloud speech API
- What is counted
- Languages and regional variants
- On device
- Not stated
- As of
- 2026-10
- Note
- Counted from the table: each of its 48 rows is one language or regional variant. 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.