Authorization
header · string · required
Use `Authorization: Token <API_KEY>`
Example: `Authorization: Token 12345abcdef`
url
body · string · required
callback
query · string · optional
URL to which we'll make the callback request
callback_method
query · string · optional
HTTP method by which the callback request will be made
default "POST"2 enum values
Values
POSTPUT
custom_intent
query · string | array · optional
Custom intents you want the model to detect within your input audio if present
custom_intent_mode
query · string · optional
Sets how the model will interpret intents submitted to the `custom_intent` param. When `strict`, the model will only return intents submitted using the `custom_intent` param. When `extended`, the model will return its own detected intents in the `custom_intent` param.
default "extended"2 enum values
Values
extendedstrict
custom_topic
query · string | array · optional
Custom topics you want the model to detect within your input audio or text if present Submit up to `100`.
custom_topic_mode
query · string · optional
Sets how the model will interpret strings submitted to the `custom_topic` param. When `strict`, the model will only return topics submitted using the `custom_topic` param. When `extended`, the model will return its own detected topics in addition to those submitted using the `custom_topic` param
default "extended"2 enum values
Values
extendedstrict
detect_entities
query · boolean · optional
Identifies and extracts key entities from content in submitted audio
default false
detect_language
query · boolean | array · optional
Identifies the dominant language spoken in submitted audio
diarize
query · boolean · optional
Deprecated: use `diarize_model` instead. Recognize speaker changes. Each word in the transcript will be assigned a speaker number starting at 0.
default false
diarize_model
query · string · optional
Select and enable a specific diarization model version. Specifying this parameter enables diarization and selects the model — you do not need to also set the deprecated `diarize=true` parameter. For batch, supported values are `latest` (currently v2), `v1`, and `v2`. For streaming, supported values are `latest` (currently v1) and `v1`; `v2` returns a validation error on streaming requests.
3 enum values
Values
latestv1v2
dictation
query · boolean · optional
Dictation mode for controlling formatting with dictated speech
default false
encoding
query · string · optional
Specify the expected encoding of your submitted audio
8 enum values
Values
linear16flacmulawamr-nbamr-wbopusspeexg729
extra
query · string | array · optional
Arbitrary key-value pairs that are attached to the API response for usage in downstream processing
filler_words
query · boolean · optional
Filler Words can help transcribe interruptions in your audio, like "uh" and "um"
default false
intents
query · boolean · optional
Recognizes speaker intent throughout a transcript or text
default false
keyterm
query · array · optional
Key term prompting can boost or suppress specialized terminology and brands. Only compatible with Nova-3
keywords
query · string | array · optional
Keywords can boost or suppress specialized terminology and brands
language
query · string · optional
The [BCP-47 language tag](https://tools.ietf.org/html/bcp47) that hints at the primary spoken language. Depending on the Model and API endpoint you choose only certain languages are available
default "en"
measurements
query · boolean · optional
Spoken measurements will be converted to their corresponding abbreviations
default false
mip_opt_out
query · boolean · optional
Opts out requests from the Deepgram Model Improvement Program. Refer to our Docs for pricing impacts before setting this to true. https://dpgr.am/deepgram-mip
default false
model
query · string | string · optional
AI model used to process submitted audio
29 enum values
Values
nova-3nova-3-generalnova-3-medicalnova-2nova-2-generalnova-2-meetingnova-2-financenova-2-conversationalainova-2-voicemailnova-2-videonova-2-medicalnova-2-drivethrunova-2-automotivenovanova-generalnova-phonecallnova-medicalenhancedenhanced-generalenhanced-meetingenhanced-phonecallenhanced-financebasemeetingphonecallfinanceconversationalaivoicemailvideo
multichannel
query · boolean · optional
Transcribe each audio channel independently
default false
numerals
query · boolean · optional
Numerals converts numbers from written format to numerical format
default false
paragraphs
query · boolean · optional
Splits audio into paragraphs to improve transcript readability
default false
profanity_filter
query · boolean · optional
Profanity Filter looks for recognized profanity and converts it to the nearest recognized non-profane word or removes it from the transcript completely
default false
punctuate
query · boolean · optional
Add punctuation and capitalization to the transcript
default false
redact
query · string | array · optional
Redaction removes sensitive information from your transcripts
replace
query · string | array · optional
Search for terms or phrases in submitted audio and replaces them
search
query · string | array · optional
Search for terms or phrases in submitted audio
sentiment
query · boolean · optional
Recognizes the sentiment throughout a transcript or text
default false
smart_format
query · boolean · optional
Apply formatting to transcript output. When set to true, additional formatting will be applied to transcripts to improve readability
default false
summarize
query · string | boolean · optional
Summarize content. For Listen API, supports string version option. For Read API, accepts boolean only.
1 enum value
Values
v2
tag
query · string | array · optional
Label your requests for the purpose of identification during usage reporting
topics
query · boolean · optional
Detect topics throughout a transcript or text
default false
utt_split
query · number · optional
Seconds to wait before detecting a pause between words in submitted audio
default 0.8
utterances
query · boolean · optional
Segments speech into meaningful semantic units
default false
version
query · string | string · optional
Version of an AI model to use
1 enum value
Values
latest
