Fact · Languages and accents
55languages
Speechmatics' documentation lists its transcription languages, and counting the table's single-language rows (not the auto option or the seven bilingual and multi-language packs) gives 55 languages for the Enhanced and Standard models.
Quote found word for word on the live source, last checked October 19, 2026
In the source's own words
“Speechmatics supports the following languages. Your ability to use any or all of them depends on the languages you are contracted to use”
Languages | Speechmatics Docs, Speechmatics, Speechmatics Docs, 2026, Transcription languages.
Open the original- What it measures
- The page is Speechmatics' own language list for its transcription models. It applies to the Enhanced and Standard models. Its table has 62 rows apart from the auto option, of which seven are bilingual or multi-language packs (Arabic and English, Malay and English, Mandarin and English, Mandarin, Malay, Tamil and English, Spanish and English, Tamil and English, and Tagalog and English), leaving 55 single languages. The page prints no total, so the count is ours.
- What it does not show
- The count is made from the table, not stated by Speechmatics. Tagalog appears only as a bilingual pack, so it is not counted. The Melia 1 and Oak 1 models are multilingual and use the same language list as hints. The page says the languages you can use depend on your contract. Speechmatics' AI information page gives '56+' languages, which does not match this table.
In the data
A row of How Many Languages Speech Recognition Supports, as Speechmatics STT (Enhanced, Standard): 55 languages.
- System
- Speechmatics transcription (Enhanced and Standard)
- Maker
- Speechmatics
- Kind
- Cloud speech API
- What is counted
- Languages
- On device
- Not stated
- As of
- 2026-10
- Note
- Not printed on the page. Counted from the 62 table rows, less the auto option and the seven bilingual or multi-language packs, which leaves 55 single languages.
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.