Languages Support

An overview of Deepgram’s speech-to-text supported languages.

language string Default: en

Pre-recorded Streaming

Enable Feature

To enable Language in your API request you can add the language parameter in the query string and set it to the language you would like to recognize:

language=OPTION

For a full list of languages and compatible models see our Model & Language Overview.

To transcribe audio from a file on your computer, run the following curl command in a terminal or your favorite API client.

cURL
$curl \
>  --request POST \
>  --header 'Authorization: Token YOUR_DEEPGRAM_API_KEY' \
>  --header 'Content-Type: audio/wav' \
>  --data-binary @youraudio.wav \
>  --url 'https://api.deepgram.com/v1/listen?language=OPTION'

Replace YOUR_DEEPGRAM_API_KEY with your Deepgram API Key.

Results

Once the language option is applied, results will appear in the transcript.

English Dialect Spelling

Deepgram’s English models are designed to handle global English audio, with strong performance across dialects and accents from across the world. Transcription outputs from the English models are provided with standardized American spelling of words.

For example, “color” will always be spelled as such with both language=en-US and language=en-GB, never using the British spelling “colour”. If your use case requires a different spelling, you should perform post-processing on results in order to enforce your preferred spelling standard.

Built with