See how Deepgram stacks up. Check out our ASR Comparison Tool. šŸŽšŸŠ

LANGUAGES

Every customer. Heard and understood.

When it comes to your customer base, a generic one-size-fits-all speech recognition model isnā€™t going to cut it. Deepgram provides the most accurate speech models in the speech-to-text industry, regardless of the language your customers speak.

Try it Free

Dozens of Languages. Multiple Form Factors.

With our team of linguists, our AI researchers have an unfair advantage. We understand the nuances of every language we build, which in turn gives you higher accuracy. Since our language models are created exclusively with End-to-End Deep Learning, we can perform transfer learning from one language to another, and quickly support new languages and dialects to better meet your use case. Donā€™t see your language listed below? Contact us, as new languages and dialects are released frequently.

More Voices. Transcribed More Accurately.

Use Case Types Available:
=General, =Conversational AI, =Earnings, =Meeting, =Phone Call, =Videos

FREE* = Free to transcribe for a limited time on our hosted environment.

View Documentation

Dutch FREE*

Did you know that Dutch and Flemish, despite the different names, are varieties of the same language, just spoken in different countries? Our model works for both, regardless of where the speaker is from. Deepgramā€™s Dutch speech recognition model is suitable for general use cases.

 

  • Dutchā€”nl

English

Over 1.348 billion people speak English as a first or second language across the globe in hundreds of different dialects. Thatā€™s why we have different speech models for the most widely spoken varieties of English. Deepgramā€™s English speech recognition models are suitable for the following dialects and use cases:

 

  • Englishā€”en Ā  Ā  Ā  Ā  Ā  Ā 
  • Englishā€”en-AU
  • Englishā€”en-US Ā  Ā  Ā  Ā  Ā  Ā 
  • Englishā€”en-GB Ā 
  • Englishā€”en-NZ Ā 
  • Englishā€”en-IN Ā 

French

French has a large number of homophonesā€”words with the same pronunciation but different spellings and meaningsā€”which is a challenge that our models can handle. Deepgramā€™s French speech recognition models are suitable for general audio use cases and the following dialects:

 

  • Frenchā€”frĀ  FREE*
  • French Canadianā€”fr-CA

German FREE*

German and English are close cousins, but even with 60% of their vocabulary sharing a common origin, one model doesnā€™t work for both. Deepgram German speech recognition model is suitable for general use cases.

 

  • Germanā€”de

Hindi

Hindi has some 37 consonants, compared to only 24 in English. But thatā€™s not a problem for Deepgramā€™s Hindi speech recognition models, which are suitable for general use cases.Ā 

 

  • Hindiā€”hi

Indonesian FREE*

Indonesian is the 9th most spoken language in the world and has approximately 160 million speakers. Deepgramā€™s Indonesian speech recognition models are suitable for general use cases.

 

  • Indonesianā€”id

Italian FREE*

Italian is spoken in a number of dialects up and down the peninsula. Our model was designed with this in mind, and works well with a range of standard Italian varieties. Deepgramā€™s Italian speech recognition model is suitable for general use cases.

 

  • Italianā€”it

Japanese FREE*

Japanese uses a combination of three different writing systems (four if you count romaji, or words written in Latin characters). We match pronunciation to the correct transcription so that it can be easily read by Japanese speakers. Deepgramā€™s Japanese speech recognition model is suitable for general use cases.

 

  • Japaneseā€”ja

Korean FREE*

Koreanā€™s own script, Hangul, is made of characters said to represent the shape of your mouth when you pronounce them. And rather than being written sound by sound, the sounds are stacked into blocks that represent syllables. Deepgramā€™s Korean speech recognition model is suitable for general use cases.

 

  • Koreanā€”ko

Mandarin FREE*

Mandarin starting developing over 1000 years ago as a language and is spoken by 14% of the world’s population. Deepgramā€™s Mandarin speech recognition model is suitable for general use cases.

 

  • Mandarin, Simplified scriptā€”
    zh (cmn-Hans-CN)
  • Mandarin, Traditional scriptā€”
    zh-TW (cmn-Hant-TW)

Portuguese

European and Brazilian Portuguese are considerably different from each other than, say, US and British English, whichĀ  is why we have two distinct speech models. Deepgramā€™s Portuguese speech recognition model is suitable for general use cases and dialects:

 

  • Portugueseā€”pt
  • Portugueseā€”pt-BR

Russian FREE*

Russian is one of the languages of space, so astronauts need to learn Russian as part of their training for the International Space Station. Luckily for Deepgram’s partnership with NASA, we can transcribe both English and Russian. Deepgramā€™s Russian speech recognition model is suitable for general use cases.

 

  • Russianā€”ru

Spanish

Spanish is an official language in 21 countries and has half a billion speakers worldwide, which means dialects matter.Ā  We created our Spanish language model to recognize a variety of regional accents and dialects, making a great fit for the diverse variety of Spanish spoken throughout the Americas. Deepgramā€™s Spanish speech recognition models are suitable for general use cases.Ā 

 

  • Spanishā€”es
  • Spanish Latin Americaā€”es-419

Swedish FREE*

Written Swedish is very close to Danish and Norwegian. The spoken languages are more distinct from each other, though, which is why we have a model specifically for Swedish. Deepgramā€™s Swedish speech recognition models are suitable for general use cases.

 

  • Swedishā€”sv

Turkish

In Turkish, one word can be equivalent to a whole sentence in another language. An example is gitmeyecekmiÅŸĆ§esine ā€˜itā€™s as if (s)he won’t leaveā€™. Luckily, our ASR model knows about all Turkish morphology to correctly transcribe roots and suffixes. Deepgramā€™s Turkish speech recognition model is suitable for general use cases.

 

  • Turkishā€”tr

Ukrainian FREE*

Our newest Ukrainian speech model is free to use, no fee, no limits. Deepgramā€™s Ukrainian speech recognition model is suitable for general use cases.

 

  • Ukrainianā€”uk

Apply Now

Receive up to $100,000 to use over 12 months.

Become a Partner

When you become a partner youā€™re in good company.

Talk to Customer Success