Features

Model

Learn about Deepgram's Model feature, which allows you to supply a model to use to process submitted audio.
Version

Learn about Deepgram's Sample Rate feature, which allows you to specify the version of the model you want to use to process your submitted audio.
Language

Learn about Deepgram's Language feature, which allows you to supply a BCP-47 language tag that hints at the primary spoken language of submitted audio.
Punctuation

Learn about Deepgrams' punctuation feature, which adds punctuation and capitalization to your transcript.
Profanity Filter

Learn about Deepgram's Profanity Filter feature, which looks for recognized profanity and converts it to the nearest recognized non-profane word or removes it from the transcript completely.
Redaction

Learn about Deepgram's Redaction feature, which redacts sensitive information, replacing redacted content with asterisks.
Diarization

Learn about Deepgram's Diarize feature, which allows you to recognizes speaker changes in submitted audio.
Named-Entity Recognition (NER)

Learn about Deepgram's Named-Entity Recognition (NER) feature, which recognizes alphanumerics in audio and removes whitespace between the characters in the transcript.
Multichannel

Learn about Deepgram's Multichannel feature, which transcribes each channel in submitted audio independently.
Numerals

Learn about Deepgram's Numerals feature, which converts numbers from written format to numerical format.
Search

Learn about Deepgram's Search feature, which searches for terms or phrases in submitted audio.
Callback

Learn about Deepgram's Callback feature, which allows you to have your submitted audio processed asynchronously.
Keywords

Learn about the keyword boosting feature available in Deepgram's API and understand how to use it to boost or suppress Out-of-vocabulary (OOV) keywords.
Utterances

Learn about the utterances feature available in Deepgram's API.
Utterance Split

Learn about Deepgram's Utterance Split feature, which detects pauses between words in submitted audio. Used when the Utterances feature is enabled for pre-recorded audio.
Interim Results

Learn about Deepgram's Interim Results feature, which provides preliminary results for streaming audio to solve the need for immediate results combined with high levels of accuracy.
Endpointing

Learn about Deepgram's Endpointing feature, which monitors incoming streaming audio and detects when a user has finished speaking or paused for a significant amount of time, indicating the completion of an idea.
Encoding

Learn about Deepgram's Encoding feature, which allows you to specify the expected encoding of your submitted audio.
Channels

Learn about Deepgram's Channels feature, which allows you to specify the number of independent audio channels your submitted audio contains. Used when the Encoding feature is also being used to submit streaming raw audio.
Sample Rate

Learn about Deepgram's Sample Rate feature, which allows you to specify the sample rate of your submitted audio. Required when the Encoding feature is also being used to submit streaming raw audio.