Speechmatics
Speechmatics develops speech models in Cambridge, England. Tony Robinson founded the business in 2006 after earlier neural-network research at Cambridge University. Its work now includes recognition models for recorded audio, live conversations, clinical speech and local device processing.
Models & tools
- Oak 1
Speechmatics · Oak
Multilingual medical recognition model for consultations that change language.
Launch date API · Provider product - Linden 1
Speechmatics · Linden
Speech recognition model for short voice-agent turns and spoken identifiers.
Launch date API - Melia 1
Speechmatics · Melia
Multilingual speech recognition model that follows language changes within a recording.
Launch date API · Provider product - Arabic–English Bilingual
Speechmatics · Bilingual recognition
Bilingual recognition model for Arabic dialects mixed with English speech.
Launch date API · Provider product - Arabic–English Medical Model
Speechmatics · Enhanced Medical
Bilingual clinical recognition model for Arabic speech mixed with English medical terms.
Launch date API · Provider product - Swedish Medical Model
Speechmatics · Enhanced Medical
Swedish clinical recognition model for specialist terms and multi-speaker consultations.
Launch date API · Provider product - Danish Medical Model
Speechmatics · Enhanced Medical
Danish clinical recognition model trained within the Nordic medical expansion.
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 - Norwegian Medical Model
Speechmatics · Enhanced Medical
Norwegian clinical recognition model for live and recorded medical conversations.
Launch date API · Provider product - German Medical Model
Speechmatics · Enhanced Medical
German clinical recognition model developed for compound terms and medical dialogue.
Launch date API · Provider product - Dutch Medical Model
Speechmatics · Enhanced Medical
Dutch clinical recognition model for medical conversations and documentation.
Launch date API · Provider product - Finnish Medical Model
Speechmatics · Enhanced Medical
Finnish clinical recognition model in Speechmatics’ Nordic medical range.
Launch date API · Provider product - French Medical Model
Speechmatics · Enhanced Medical
French clinical recognition model for medical dialogue and specialist terms.
Launch date API · Provider product - Spanish Medical Model
Speechmatics · Enhanced Medical
Spanish clinical recognition model for specialist vocabulary and patient conversations.
Launch date API · Provider product - English Medical Model
Speechmatics · Enhanced Medical
English clinical recognition model trained for medical terminology and fast dialogue.
Launch date API · Provider product - Tagalog–English Bilingual
Speechmatics · Bilingual recognition
Bilingual recognition model for Tagalog and English within the same recording.
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 - Mandarin–English Bilingual
Speechmatics · Bilingual recognition
Bilingual recognition model trained for Mandarin and English code-switching in Southeast Asia.
Launch date API · Provider product - Tamil–English Bilingual
Speechmatics · Bilingual recognition
Bilingual recognition model for Tamil and English speech in the same conversation.
Launch date API · Provider product - Ursa 2
Speechmatics · Ursa
Historical recognition generation that expanded self-supervised training and language coverage.
Launch date Access not confirmed - Spanish–English Bilingual
Speechmatics · Bilingual recognition
Bilingual recognition model that transcribes Spanish and English in one stream.
Launch date API · Provider product - Ursa
Speechmatics · Ursa
Historical recognition generation with self-supervised audio representations and separate decoding components.
Launch date Access not confirmed - Autonomous Speech Recognition
Speechmatics · Autonomous ASR
Historical self-supervised recognition release trained on a much larger audio collection.
Launch date Access not confirmed - English Finance Model
Speechmatics · Domain recognition
Specialist English recognition model for financial vocabulary, with current access unconfirmed.
Launch date not confirmedAccess not confirmed - Enhanced
Speechmatics · Enhanced
General speech recognition model that prioritizes accuracy across supported language packs.
Launch date not confirmedAPI · Provider product - On-Device Speech Recognition
Speechmatics · On-Device
Local speech recognition model family for software running on user devices.
Launch date not confirmedRestricted accessProvider product - Standard
Speechmatics · Standard
General speech recognition model that prioritizes transcription throughput.
Launch date not confirmedAPI · Provider product - Text-to-Speech Preview
Speechmatics · Speechmatics TTS
English speech synthesis models with streamed audio and four selectable voices.
Launch date not confirmedPreviewAPI · Provider product