Mandarin–English Bilingual
The Mandarin–English model appeared in the May 2025 container release. The July announcement describes its role in the Southeast Asian bilingual range.
Regional conversation data
Speechmatics says it worked with local partners and trained new models on regional datasets. The Mandarin–English release was not just a sequence of calls to separate monolingual services.Speechmatics: Three Southeast Asian bilingual models
The follow-up development account reports baseline Mandarin improvements as part of the bilingual release. This separates progress on the individual language from progress at the point where a speaker changes language.Speechmatics: Southeast Asian language model development
Practical guidance. For mixed Mandarin and English captions, inspect the word sequence across each switch. A correct transcript in one language can hide omissions at the boundary.Speechmatics: Southeast Asian language model development
Specifications & access
| Detail | Value and conditions |
|---|---|
| Launch date | |
| Access | API, Provider product |
| Model identifiers | Mandarin Englishcmn_en |
| Language selector | cmn_enSpeechmatics documentation: Languages and medical coverage |
Related models
- Melia 1
Speechmatics · Melia
Multilingual speech recognition model that follows language changes within a recording.
Launch date API · Provider product - Mandarin–Malay–Tamil–English
Speechmatics · Multilingual language packs
Four-language recognition model for English, Mandarin, Malay and Tamil conversation.
Launch date API · Provider product - Malay–English Bilingual
Speechmatics · Bilingual recognition
Bilingual recognition model for Malay conversation mixed with English terms.
Launch date API · Provider product