Live Audio

API key for authentication. Format should be be either ‘token <DEEPGRAM_API_KEY>’ or ‘Bearer <JWT_TOKEN>’

URL to which we’ll make the callback request

HTTP method by which the callback request will be made

The number of channels in the submitted audio

Defaults to false. Recognize speaker changes. Each word in the transcript will be assigned a speaker number starting at 0

Identify and extract key entities from content in submitted audio

Specify the expected encoding of your submitted audio

Indicates how long Deepgram will wait to detect whether a speaker has finished speaking or pauses for a significant period of time. When set to a value, the streaming endpoint immediately finalizes the transcription for the processed time range and returns the transcript with a speech_final parameter set to true. Can also be set to false to disable endpointing

Arbitrary key-value pairs that are attached to the API response for usage in downstream processing

Filler Words can help transcribe interruptions in your audio, like “uh” and “um”

Specifies whether the streaming endpoint should provide ongoing transcription updates as more audio is received. When set to true, the endpoint sends continuous updates, meaning transcription results may evolve over time

Key term prompting can boost or suppress specialized terminology and brands. Only compatible with Nova-3

Keywords can boost or suppress specialized terminology and brands

The BCP-47 language tag that hints at the primary spoken language. Depending on the Model you choose only certain languages are available

AI model to use for the transcription

Transcribe each audio channel independently

Convert numbers from written format to numerical format

Profanity Filter looks for recognized profanity and converts it to the nearest recognized non-profane word or removes it from the transcript completely

Add punctuation and capitalization to the transcript

Redaction removes sensitive information from your transcripts

Search for terms or phrases in submitted audio and replaces them

Sample rate of submitted audio. Required (and only read) when a value is provided for encoding

Search for terms or phrases in submitted audio

Apply formatting to transcript output. When set to true, additional formatting will be applied to transcripts to improve readability

Label your requests for the purpose of identification during usage reporting

Indicates how long Deepgram will wait to send an UtteranceEnd message after a word has been transcribed. Use with interim_results

Indicates that speech has started. You’ll begin receiving Speech Started messages upon speech starting

Version of an AI model to use