POST /accounts/{account_id}/ai/run/@cf/deepgram/nova-3

Servers

Path parameters

Name Type Required Description
account_id String Yes

Request headers

Name Type Required Description
Content-Type String Yes The media type of the request body.

Default value: "application/json"

Query parameters

Name Type Required Description
queueRequest String No

Request body fields

Name Type Required Description
vad_events Boolean No

Indicates that speech has started. You'll begin receiving Speech Started messages upon speech starting. Note: Supported only for webosockets.

extra String No

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

utt_split Number No

Seconds to wait before detecting a pause between words in submitted audio.

custom_topic String No

Custom topics you want the model to detect within your input audio or text if present Submit up to 100

measurements Boolean No

Spoken measurements will be converted to their corresponding abbreviations.

audio Object Yes
audio.contentType String Yes
audio.body Object Yes
custom_topic_mode String No

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.

Valid values:

  • "extended"
  • "strict"
sentiment Boolean No

Recognizes the sentiment throughout a transcript or text.

mip_opt_out Boolean No

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.

redact String No

Redaction removes sensitive information from your transcripts.

multichannel Boolean No

Transcribe each audio channel independently.

custom_intent String No

Custom intents you want the model to detect within your input audio if present

utterances Boolean No

Segments speech into meaningful semantic units.

replace String No

Search for terms or phrases in submitted audio and replaces them.

topics Boolean No

Detect topics throughout a transcript or text.

language String No

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

utterance_end_ms Boolean No

Indicates how long model will wait to send an UtteranceEnd message after a word has been transcribed. Use with interim_results. Note: Supported only for webosockets.

channels Number No

The number of channels in the submitted audio

filler_words Boolean No

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

profanity_filter Boolean No

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

search String No

Search for terms or phrases in submitted audio.

dictation Boolean No

Identify and extract key entities from content in submitted audio

mode String No

Mode of operation for the model representing broad area of topic that will be talked about in the supplied audio

Valid values:

  • "general"
  • "medical"
  • "finance"
custom_intent_mode String No

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 addition those submitted using the custom_intents param

Valid values:

  • "extended"
  • "strict"
detect_entities Boolean No

Identifies and extracts key entities from content in submitted audio

endpointing String No

Indicates how long model 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

smart_format Boolean No

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

keywords String No

Keywords can boost or suppress specialized terminology and brands.

detect_language Boolean No

Identifies the dominant language spoken in submitted audio

keyterm String No

Key term prompting can boost or suppress specialized terminology and brands.

paragraphs Boolean No

Splits audio into paragraphs to improve transcript readability.

numerals Boolean No

Numerals converts numbers from written format to numerical format.

encoding String No

Specify the expected encoding of your submitted audio

Valid values:

  • "g729"
  • "speex"
  • "amr-nb"
  • "opus"
  • "linear16"
  • "flac"
  • "mulaw"
  • "amr-wb"
interim_results Boolean No

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. Note: Supported only for webosockets.

diarize Boolean No

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

punctuate Boolean No

Add punctuation and capitalization to the transcript.

How to start integrating

  1. Add HTTP Task to your workflow definition.
  2. Search for the API you want to integrate with and click on the name.
    • This loads the API reference documentation and prepares the Http request settings.
  3. Click Test request to test run your request to the API and see the API's response.