Dictation

Pre-recorded Streaming:NovaStreaming: Flux English (all available regions)

Dictation is a feature of Deepgram’s Speech-to-Text API that converts spoken dictation commands into their corresponding punctuation marks.

This feature enhances the readability of transcriptions by accurately representing verbal commands as punctuation. For example, saying “comma” as a word will be transcribed as the punctuation mark ”,”.

To enable Dictation, set the dictation parameter to true in your API request. Note that the punctuate parameter must also be enabled for Dictation to work.

To transcribe audio with dictation enabled, run the following cURL command in a terminal or your favorite API client:

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?dictation=true&punctuate=true'

Once dictation is enabled, the results will appear in the transcript with the spoken commands converted to punctuation marks. Below is an example of what the transcript will look like when dictation is enabled.

Patient presents with a headache comma nausea comma and vomiting period They report the headache started two days ago period Vital signs are within normal limits period

Patient presents with a headache, nausea, and vomiting. They report the headache started two days ago. Vital signs are within normal limits.

In the response example above, spoken commands such as “comma” and “period” have been converted to their corresponding punctuation marks, making the transcription more readable and easier to understand.

The following commands will be converted.