API Reference

Deepgram's API gives you streamlined access to Deepgram products, including automatic transcription from Deepgram's off-the-shelf and trained speech recognition models, and to all of your Deepgram resources, such as your account's projects, API keys, billing settings and balances, and usage statistics.

Our SDKs make integrating and interacting with our API quick and easy.

Endpoint

https://api.deepgram.com/v1

Authentication

Send requests to the API with an Authorization header that references your project's API Key:

Authorization: Token <YOUR_DEEPGRAM_API_KEY>

You can create a Deepgram API Key in the Deepgram Console. You must create your first API Key using the Console.

All API requests must be made over HTTPS. Calls made over plain HTTP will fail. API requests made without authentication will also fail.

Security Scheme Type	API Key
Header parameter name:	Authorization

Transcription

High-speed transcription of either pre-recorded or streaming audio. This feature is very fast, can understand nearly every audio format available, and is customizable. You can customize your transcript using various query parameters and apply general purpose and custom-trained AI models.

Deepgram supports over 100 different audio formats and encodings. For example, some of the most common audio formats and encodings we support include MP3, MP4, MP2, AAC, WAV, FLAC, PCM, M4A, Ogg, Opus, and WebM. However, because audio format is largely unconstrained, we always recommend to ensure compatibility by testing small sets of audio when first operating with new audio sources.

Transcribe Pre-recorded Audio

Transcribes the specified audio file.

Deepgram does not store transcriptions. Make sure to save output or return transcriptions to a callback URL for custom processing.

Query Parameters

tier:

string

Level of model you would like to use in your request. Options include:

enhanced:
Applies our newest, most powerful ASR models; they generally have higher accuracy and better word recognition than our Base models, and they handle uncommon words significantly better.
base: (Default)
Applies our Base models, which are built on our signature end-to-end deep learning speech model architecture and offer a solid combination of accuracy and cost effectiveness.

To learn more, see Features: Tier.

model:

string

AI model used to process submitted audio. Options include:

general: (Default)
Optimized for everyday audio processing.
TIERS: enhanced, base
meeting:
Optimized for conference room settings, which include multiple speakers with a single microphone.
TIERS: enhanced beta, base
phonecall:
Optimized for low-bandwidth audio phone calls.
TIERS: enhanced beta, base
voicemail:
Optimized for low-bandwidth audio clips with a single speaker. Derived from the phonecall model.
TIERS: base
finance:
Optimized for multiple speakers with varying audio quality, such as might be found on a typical earnings call. Vocabulary is heavily finance oriented.
TIERS: enhanced beta, base
conversationalai:
Optimized to allow artificial intelligence technologies, such as chatbots, to interact with people in a human-like way.
TIERS: base
video:
Optimized for audio sourced from videos.
TIERS: base
<custom_id>:
To use a custom model associated with your account, include its custom_id.
TIERS: enhanced, base (depending on which tier the custom model was trained on)

To learn more, see Features: Model.

version:

string

Version of the model to use.

Default: latest

Possible values: latest OR <version_id>

To learn more, see Features: Version.

language:

string

BCP-47 language tag that hints at the primary spoken language. Language support is optimized for the following language/model combinations:

Chinese

zh-CN: China (Simplified Mandarin) beta
MODELS: general
zh-TW: Taiwan (Traditional Mandarin) beta
MODELS: general

Dutch

nl: beta
MODELS: general (enhanced, base)

English

en: English (Default)
MODELS: general (enhanced, base), meeting (enhanced beta, base), phonecall (enhanced beta, base), voicemail, finance (enhanced beta, base), conversationalai, video
en-AU: Australia
MODELS: general
en-IN: India
MODELS: general
en-NZ: New Zealand
MODELS: general
en-GB: United Kingdom
MODELS: general
en-US: United States
MODELS: general (enhanced, base), meeting (enhanced beta, base), phonecall (enhanced beta, base), voicemail, finance, conversationalai, video

Flemish

nl: beta
MODELS: general (enhanced, base)

French

fr:
MODELS: general
fr-CA: Canada
MODELS: general

German

de:
MODELS: general

Hindi

hi:
MODELS: general
hi-Latn: Roman Script beta
MODELS: general

Indonesian

id: beta
MODELS: general

Italian

it: beta
MODELS: enhanced, general

Japanese

ja: beta
MODELS: enhanced, general

Korean

ko: beta
MODELS: enhanced, general

Polish

pl: beta
MODELS: general

Portuguese

pt:
MODELS: enhanced beta, general
pt-BR: Brazil
MODELS: enhanced beta, general
pt-PT: Portugal
MODELS: enhanced beta, general

Russian

ru:
MODELS: general

Spanish

es:
MODELS: general (enhanced beta, base)
es-419: Latin America
MODELS: general

Swedish

sv: beta
MODELS: general

Turkish

tr:
MODELS: general

Ukrainian

uk: beta
MODELS: general

To learn more, see Features: Language.

detect-language:

boolean

Indicates whether to detect the language of the provided audio. To learn more, see Features: Language Detection.

punctuate:

boolean

Indicates whether to add punctuation and capitalization to the transcript. To learn more, see Features: Punctuation.

profanity_filter:

boolean

Indicates whether to remove profanity from the transcript. To learn more, see Features: Profanity Filter.

redact:

any

Indicates whether to redact sensitive information, replacing redacted content with asterisks (*). Options include:

pci:
Redacts sensitive credit card information, including credit card number, expiration date, and CVV.
numbers: (or true)
Aggressively redacts strings of numerals.
ssn: beta
Redacts social security numbers.

Can send multiple instances in query string (for example, redact=pci&redact=numbers). When sending multiple values, redaction occurs in the order you specify. For instance, in this example, sensitive credit card information would be redacted first, then strings of numbers.

To learn more, see Features: Redaction.

diarize:

boolean

Indicates whether to recognize speaker changes. When set to true, each word in the transcript will be assigned a speaker number starting at 0.

To use the legacy diarization feature, add a diarize_version parameter set to 2021-07-14.0. For example, diarize_version=2021-07-14.0.

To learn more, see Features: Diarization.

diarize_version:

string

Indicates the version of the diarization feature to use. To use the legacy diarization feature, set the parameter value to 2021-07-14.0.

Only used when the diarization feature is enabled (diarize=true is passed to the API).

To learn more, see Features: Diarization.

ner:

boolean

Indicates whether to recognize alphanumeric strings. When set to true, whitespace will be removed between characters identified as part of an alphanumeric string. To learn more, see Features: Named-Entity Recognition (NER).

multichannel:

boolean

Indicates whether to transcribe each audio channel independently. When set to true, you will receive one transcript for each channel, which means you can apply a different model to each channel using the model parameter (e.g., set model to general:phonecall, which applies the general model to channel 0 and the phonecall model to channel 1).

To learn more, see Features: Multichannel.

alternatives:

integer

Maximum number of transcript alternatives to return. Just like a human listener, Deepgram can provide multiple possible interpretations of what it hears.

Default: 1

numerals:

boolean

Indicates whether to convert numbers from written format (e.g., one) to numerical format (e.g., 1).

Deepgram can format numbers up to 999,999.

Converted numbers do not include punctuation. For example, 999,999 would be transcribed as 999999.

To learn more, see Features: Numerals.

search:

any

Terms or phrases to search for in the submitted audio. Deepgram searches for acoustic patterns in audio rather than text patterns in transcripts because we have noticed that acoustic pattern matching is more performant.

Can include up to 25 search terms per request.
Can send multiple instances in query string (for example, search=speech&search=Friday).

To learn more, see Features: Search.

replace:

string

Terms or phrases to search for in the submitted audio and replace.

URL-encode any terms or phrases that include spaces, punctuation, or other special characters.
Can send multiple instances in query string (for example, replace=this:that&replace=thisalso:thatalso).
Replacing a term or phrase with nothing (replace=this) will remove the term or phrase from the audio transcript.

To learn more, see Features: Replace.

callback:

string

Callback URL to provide if you would like your submitted audio to be processed asynchronously. When passed, Deepgram will immediately respond with a request_id. When it has finished analyzing the audio, it will send a POST request to the provided URL with an appropriate HTTP status code.

Notes:

You may embed basic authentication credentials in the callback URL.
Only ports 80, 443, 8080, and 8443 can be used for callbacks

To learn more, see Features: Callback.

keywords:

any

Keywords to which the model should pay particular attention to boosting or suppressing to help it understand context. Just like a human listener, Deepgram can better understand mumbled, distorted, or otherwise hard-to-decipher speech when it knows the context of the conversation.

Notes:

Can include up to 200 keywords per request.
Can send multiple instances in query string (for example, keywords=medicine&keywords=prescription).
Can request multi-word keywords in a percent-encoded query string (for example, keywords=miracle%20medicine). When Deepgram listens for your supplied keywords, it separates them into individual words, then boosts or suppresses them individually.
Can append a positive or negative intensifier to either boost or suppress the recognition of particular words. Positive and negative values can be decimals.
Follow best practices for keyword boosting.
Support for out-of-vocabulary (OOV) keyword boosting when processing streaming audio is currently in beta; to fall back to previous keyword behavior, append the query parameter keyword_boost=legacy to your API request.

To learn more, see Features: Keywords.

paragraphs:

boolean

Indicates whether Deepgram will split audio into paragraphs to improve transcript readability. When paragraphs is set to true, you must also set either punctuate, diarize, or multichannel to true.

To learn more, see Features: Paragraphs.

summarize:

boolean

Indicates whether Deepgram will provide summaries for sections of content. When summarize is set to true, punctuate will be set to true by default.

To learn more, see Features: Summarize.

utterances:

boolean

Indicates whether Deepgram will segment speech into meaningful semantic units, which allows the model to interact more naturally and effectively with speakers' spontaneous speech patterns. For example, when humans speak to each other conversationally, they often pause mid-sentence to reformulate their thoughts, or stop and restart a badly-worded sentence. When utterances is set to true, these utterances are identified and returned in the transcript results.

By default, when utterances is enabled, it starts a new utterance after 0.8 s of silence. You can customize the length of time used to determine where to split utterances by submitting the utt_split parameter.

To learn more, see Features: Utterances.

utt_split:

number

Length of time in seconds of silence between words that Deepgram will use when determining where to split utterances. Used when utterances is enabled.

Default: 0.8

To learn more, see Features: Utterance Split.

tag:

string

Tag to associate with the request. Your request will automatically be associated with any tags you add to the API Key used to run the request. Tags associated with requests appear in usage reports.

To learn more, see Features: Tag.

Request Body Schema

Request body when submitting pre-recorded audio. Accepts either:

raw binary audio data. In this case, include a Content-Type header set to the audio MIME type.
JSON object with a single field from which the audio can be retrieved. In this case, include a Content-Type header set to application/json.

url:

string

URL of audio file to transcribe.

Responses

Status	Description
200 Success	Audio submitted for transcription.

Response Schema

metadata: object

JSON-formatted ListenMetadata object.
- request_id: uuid
  
  Unique identifier of the submitted audio and derived data returned.
- transaction_key: string
  
  Blob of text that helps Deepgram engineers debug any problems you encounter. If you need help getting an API call to work correctly, send this key to us so that we can use it as a starting point when investigating any issues.
- sha256: string
  
  SHA-256 hash of the submitted audio data.
- created: string
  
  ISO-8601 timestamp that indicates when the audio was submitted.
- duration: number
  
  Duration in seconds of the submitted audio.
- channels: integer
  
  Number of channels detected in the submitted audio.
results: object

JSON-formatted ListenResults object.
- channels: array
  
  Array of JSON-formatted ChannelResult objects.
  - search: array
    
    Array of JSON-formatted SearchResults.
    - query: string
      
      Term for which Deepgram is searching.
    - hits: array
      
      Array of JSON-formatted Hit objects.
      - confidence: number
        
        Value between 0 and 1 that indicates the model's relative confidence in this hit.
      - start: number
        
        Offset in seconds from the start of the audio to where the hit occurs.
      - end: number
        
        Offset in seconds from the start of the audio to where the hit ends.
      - snippet: string
        
        Transcript that corresponds to the time between start and end.
  - alternatives: array
    
    Array of JSON-formatted ResultAlternative objects. This array will have length n, where n matches the value of the alternatives parameter passed in the request body.
    - transcript: string
      
      Single-string transcript containing what the model hears in this channel of audio.
    - confidence: number
      
      Value between 0 and 1 indicating the model's relative confidence in this transcript.
    - words: array
      
      Array of JSON-formatted Word objects.
      - word: string
        
        Distinct word heard by the model.
      - start: number
        
        Offset in seconds from the start of the audio to where the spoken word starts.
      - end: number
        
        Offset in seconds from the start of the audio to where the spoken word ends.
      - confidence: number
        
        Value between 0 and 1 indicating the model's relative confidence in this word.

Endpoint

POST /listen

Transcribe Live Streaming Audio

Deepgram provides its customers with real-time, streaming transcription via its streaming endpoints. These endpoints are high-performance, full-duplex services running over the tried-and-true WebSocket protocol, which makes integration with customer pipelines simple due to the wide array of client libraries available.

To use this endpoint, connect to wss://api.deepgram.com/v1/listen. TLS encryption will protect your connection and data. We support a minimum of TLS 1.2.

All data is sent to the streaming endpoint as binary-type WebSocket messages containing payloads that are the raw audio data. Because the protocol is full-duplex, you can stream in real-time and still receive transcription responses while uploading data.

When you are finished, send an empty (length zero) binary message to the server. The server will interpret it as a shutdown command, which means it will finish processing whatever data is still has cached, send the response to the client, send a summary metadata object, and then terminate the WebSocket connection.

To learn more about working with real-time streaming data and results, see Get Started with Streaming Audio.

Deepgram does not store transcriptions. Make sure to save output or return transcriptions to a callback URL for custom processing.

Query Parameters

tier:

string

Level of model you would like to use in your request. Options include:

enhanced:
Applies our newest, most powerful ASR models; they generally have higher accuracy and better word recognition than our Base models, and they handle uncommon words significantly better.
base: (Default)
Applies our Base models, which are built on our signature end-to-end deep learning speech model architecture and offer a solid combination of accuracy and cost effectiveness.

To learn more, see Features: Tier.

model:

string

AI model used to process submitted audio. Options include:

general: (Default)
Optimized for everyday audio processing.
TIERS: enhanced, base
meeting:
Optimized for conference room settings, which include multiple speakers with a single microphone.
TIERS: enhanced beta, base
phonecall:
Optimized for low-bandwidth audio phone calls.
TIERS: enhanced beta, base
voicemail:
Optimized for low-bandwidth audio clips with a single speaker. Derived from the phonecall model.
TIERS: base
finance:
Optimized for multiple speakers with varying audio quality, such as might be found on a typical earnings call. Vocabulary is heavily finance oriented.
TIERS: enhanced beta, base
conversationalai:
Optimized to allow artificial intelligence technologies, such as chatbots, to interact with people in a human-like way.
TIERS: base
video:
Optimized for audio sourced from videos.
TIERS: base
<custom_id>:
To use a custom model associated with your account, include its custom_id.
TIERS: enhanced, base (depending on which tier the custom model was trained on)

To learn more, see Features: Model.

version:

string

Version of the model to use.

Default: latest

Possible values: latest OR <version_id>

To learn more, see Features: Version.

language:

string

BCP-47 language tag that hints at the primary spoken language. Language support is optimized for the following language/model combinations:

Chinese

zh-CN: China (Simplified Mandarin) beta
MODELS: general
zh-TW: Taiwan (Traditional Mandarin) beta
MODELS: general

Dutch

nl: beta
MODELS: general (enhanced, base)

English

en: English (Default)
MODELS:general (enhanced, base), meeting (enhanced beta, base), phonecall (enhanced beta, base), voicemail, finance (enhanced beta, base), conversationalai, video
en-AU: Australia
MODELS: general
en-IN: India
MODELS: general
en-NZ: New Zealand
MODELS: general
en-GB: United Kingdom
MODELS: general
en-US: United States
MODELS: general (enhanced, base), meeting (enhanced beta, base), phonecall (enhanced beta, base), voicemail, finance (enhanced beta, base), conversationalai, video

Flemish

nl: beta
MODELS: general (enhanced, base)

French

fr:
MODELS: general
fr-CA: Canada
MODELS: general

German

de:
MODELS: general

Hindi

hi:
MODELS: general
hi-Latn: Roman Script beta
MODELS: general

Indonesian

id: beta
MODELS: general

Italian

it: beta
MODELS: enhanced, general

Japanese

ja: beta
MODELS: enhanced, general

Korean

ko: beta
MODELS: enhanced, general

Polish

pl: beta
MODELS: general

Portuguese

pt:
MODELS: enhanced beta, general
pt-BR: Brazil
MODELS: enhanced beta, general
pt-PT: Portugal
MODELS: enhanced beta, general

Russian

ru:
MODELS: general

Spanish

es:
MODELS: general (enhanced beta, base)
es-419: Latin America
MODELS: general

Swedish

sv: beta
MODELS: general

Turkish

tr:
MODELS: general

Ukrainian

uk: beta
MODELS: general

To learn more, see Features: Language.

punctuate:

boolean

Indicates whether to add punctuation and capitalization to the transcript. To learn more, see Features: Punctuation.

profanity_filter:

boolean

Indicates whether to remove profanity from the transcript. To learn more, see Features: Profanity Filter.

redact:

any

Indicates whether to redact sensitive information, replacing redacted content with asterisks (*). Options include:

pci:

Redacts sensitive credit card information, including credit card number, expiration date, and CVV.
numbers: (or true)

Aggressively redacts strings of numerals.
ssn: beta

Redacts social security numbers.

To learn more, see Features: Redaction.

diarize:

boolean

Indicates whether to recognize speaker changes. When set to true, each word in the transcript will be assigned a speaker number starting at 0.

To use the legacy diarization feature, add a diarize_version parameter set to 2021-07-14.0. For example, diarize_version=2021-07-14.0.

To learn more, see Features: Diarization.

diarize_version:

string

Indicates the version of the diarization feature to use. To use the legacy diarizer, set the parameter value to 2021-07-14.0.

Only used when the diarization feature is enabled (diarize=true is passed to the API).

To learn more, see Features: Diarization.

ner:

boolean

multichannel:

boolean

To learn more, see Features: Multichannel.

alternatives:

integer

Maximum number of transcript alternatives to return. Just like a human listener, Deepgram can provide multiple possible interpretations of what it hears.

Default: 1

numerals:

boolean

Indicates whether to convert numbers from written format (e.g., one) to numerical format (e.g., 1).

Deepgram can format numbers up to 999,999.

Converted numbers do not include punctuation. For example, 999,999 would be transcribed as 999999.

To learn more, see Features: Numerals.

search:

any

Can include up to 25 search terms per request.
Can send multiple instances in query string (for example, search=speech&search=Friday).

To learn more, see Features: Search.

replace:

string

Terms or phrases to search for in the submitted audio and replace.

URL-encode any terms or phrases that include spaces, punctuation, or other special characters.
Can send multiple instances in query string (for example, replace=this:that&replace=thisalso:thatalso).
Replacing a term or phrase with nothing (replace=this) will remove the term or phrase from the audio transcript.

To learn more, see Features: Replace.

callback:

string

Notes:

You may embed basic authentication credentials in the callback URL.
Only ports 80, 443, 8080, and 8443 can be used for callbacks

For streaming audio, callback can be used to redirect streaming responses to a different server:

If the callback URL begins with http:// or https://, then POST requests are sent to the callback server for each streaming response.
If the callback URL begins with ws:// or wss://, then a WebSocket connection is established with the callback server and WebSocket text messages are sent containing the streaming responses.
If a WebSocket callback connection is disconnected at any point, the entire real-time transcription stream is killed; this maintains the strong guarantee of a one-to-one relationship between incoming real-time connections and outgoing WebSocket callback connections.

To learn more, see Features: Callback.

keywords:

any

Notes:

Can include up to 200 keywords per request.
Can send multiple instances in query string (for example, keywords=medicine&keywords=prescription).
Can request multi-word keywords in a percent-encoded query string (for example, keywords=miracle%20medicine). When Deepgram listens for your supplied keywords, it separates them into individual words, then boosts or suppresses them individually.
Can append a positive or negative intensifier to either boost or suppress the recognition of particular words. Positive and negative values can be decimals.
Follow best practices for keyword boosting.
Support for out-of-vocabulary (OOV) keyword boosting when processing streaming audio is currently in beta; to fall back to previous keyword behavior, append the query parameter keyword_boost=legacy to your API request.

To learn more, see Features: Keywords.

interim_results:

boolean

Indicates whether the streaming endpoint should send you updates to its transcription as more audio becomes available. When set to true, the streaming endpoint returns regular updates, which means transcription results will likely change for a period of time. By default, this flag is set to false.

When the flag is set to false, latency increases (usually by several seconds) because the server needs to stabilize the transcription before returning the final results for each piece of incoming audio. If you want the lowest-latency streaming available, then set interim_results to true and handle the corrected transcripts as they are returned.

To learn more, see Features: Interim Results.

endpointing:

boolean

Indicates whether Deepgram will detect whether a speaker has finished speaking (or paused for a significant period of time, indicating the completion of an idea). When Deepgram detects an endpoint, it assumes that no additional data will improve its prediction, so it immediately finalizes the result for the processed time range and returns the transcript with a speech_final parameter set to true.

For example, if you are working with a 15-second audio clip, but someone is speaking for only the first 3 seconds, endpointing allows you to get a finalized result after the first 3 seconds.

By default, endpointing is enabled and finalizes a transcript after 10 ms of silence. You can customize the length of time used to detect whether a speaker has finished speaking by submitting the vad_turnoff parameter.

Default: true

To learn more, see Features: Endpointing.

vad_turnoff:

integer

Length of time in milliseconds of silence that voice activation detection (VAD) will use to detect that a speaker has finished speaking. Used when endpointing is enabled. Defaults to 10 ms. Deepgram customers may configure a value between 10 ms and 5000 ms; on-premise customers may remove this restriction.

Default: 10

To learn more, see Features: Voice Activity Detection (VAD).

encoding:

string

Expected encoding of the submitted streaming audio.

Options include:

linear16: 16-bit, little endian, signed PCM WAV data
flac: FLAC-encoded data
mulaw: mu-law encoded WAV data
amr-nb: adaptive multi-rate narrowband codec (sample rate must be 8000)
amr-wb: adaptive multi-rate wideband codec (sample rate must be 16000)
opus: Ogg Opus
speex: Ogg Speex

Only required when raw, headerless audio packets are sent to the streaming service. For pre-recorded audio or audio submitted to the standard /listen endpoint, we support over 40 popular codecs and do not require this parameter.

To learn more, see Features: Encoding.

channels:

integer

Number of independent audio channels contained in submitted streaming audio. Only read when a value is provided for encoding.

Default: 1

To learn more, see Features: Channels.

sample_rate:

integer

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

To learn more, see Features: Sample Rate.

tag:

string

Tag to associate with the request. Your request will automatically be associated with any tags you add to the API Key used to run the request. Tags associated with requests appear in usage reports.

To learn more, see Features: Tag.

Responses

Status	Description
201 Success	Audio submitted for transcription.

Response Schema

channel_index: array

Information about the active channel in the form [channel_index, total_number_of_channels].
duration: number

Duration in seconds.
start: number

Offset in seconds.
is_final: boolean

Indicates that Deepgram has identified a point at which its transcript has reached maximum accuracy and is sending a definitive transcript of all audio up to that point. To learn more, see Features: Interim Results.
speech_final: boolean

Indicates that Deepgram has detected an endpoint and immediately finalized its results for the processed time range. To learn more, see Features: Endpointing.
channel: object
- alternatives: array
  
  Array of JSON-formatted ResultAlternative objects. This array will have length n, where n matches the value of the alternatives parameter passed in the request body.
  - transcript: string
    
    Single-string transcript containing what the model hears in this channel of audio.
  - confidence: number
    
    Value between 0 and 1 indicating the model's relative confidence in this transcript.
  - words: array
    
    Array of JSON-formatted Word objects.
    - word: string
      
      Distinct word heard by the model.
    - start: number
      
      Offset in seconds from the start of the audio to where the spoken word starts.
    - end: number
      
      Offset in seconds from the start of the audio to where the spoken word ends.
    - confidence: number
      
      Value between 0 and 1 indicating the model's relative confidence in this word.
metadata: object
- request_id: uuid
  
  Unique identifier of the submitted audio and derived data returned.

Error Handling

If Deepgram encounters an error during real-time streaming, we will return a WebSocket Close frame (WebSocket Protocol specification, section 5.5.1]).

The body of the Close frame will indicate the reason for closing using one of the specification’s pre-defined status codes followed by a UTF-8-encoded payload that represents the reason for the error. Current codes and payloads in use include:

Code	Payload	Description
1002	DATA-0000	The payload cannot be decoded as audio. It is either not audio data or is a codec unsupported by Deepgram.
1011	NET-0000	The service has not transmitted a Text frame to the client within the timeout window. This may indicate an issue internally in Deepgram's systems or could be due to Deepgram not receiving enough audio data to transcribe a frame.
1011	NET-0001	The service has not received a Binary frame from the client within the timeout window. This may indicate an internal issue in Deepgram's systems, the client's systems, or the network connecting them.

After sending a Close message, the endpoint considers the WebSocket connection closed and will close the underlying TCP connection.

Endpoint

WSS /listen

Projects

A Project organizes all of your Deepgram resources, including your datasets and models, into logical groups. Projects also give you access to API keys and billing settings for Deepgram services.

Get Projects

Retrieves basic information about the specified project.

Required account/project scope(s): project:read.

Responses

Status	Description
200 Success	Projects found.

Response Schema

projects: array

Array of project objects.
- project_id: uuid
  
  Unique identifier of the project.
- name: string
  
  Name of the project.
- company: string
  
  Name of the company associated with the project. Optional.

Endpoint

GET /projects

Get Project

Query Parameters

project_id: uuid

Unique identifier of the project for which you want to retrieve information.

Responses

Status	Description
200 Success	Project found.
404 Not Found	A project with the specified ID was not found.

Response Schema

project_id: uuid

Unique identifier of the project.
name: string

Name of the project.
company: string

Name of the company associated with the project. Optional.

Endpoint

GET /projects/{project_id}

Update Project

Updates the specified project.

Required account scope(s): project:write. Required project scope(s): project:write:settings.

Path Parameters

project_id: uuid

Unique identifier of the project that you want to update.

Request Body Schema

name: string

Name of the project. Optional.

company: string

Name of the company associated with the project. Optional.

Responses

Status	Description
200 Success	Project updated.

Response Schema

message: string

Success message.

Endpoint

PATCH /projects/{project_id}

Delete Project

Deletes the specified project.

Required account scope(s): project:write. Required project scope(s): project:write:destroy.

Path Parameters

project_id: uuid

Unique identifier of the project that you want to delete.

Responses

Status	Description
200 Success	Project deleted.

Endpoint

DELETE /projects/{project_id}

Keys

Keys are associated with Deepgram Projects. They enable you to use the Deepgram API, identify the Project calling the API, and associate usage information with Projects. Keys are assigned Scopes, which determine which actions they can be used to perform in the associated Project. For each Project, you can create multiple Keys and assign different Scopes for each Key.

Get Keys

Retrieves keys for the specified project. If the authenticated account has access to the members:read, admins:read, and owners:read project scopes, it will list all keys for the project. Otherwise, it will only list keys that belong to the authenticated account.

Required account/project scope(s): keys:read. Optional project scope(s): members:read, admins:read, owners:read.

Path Parameters

project_id: uuid

Unique identifier of the project for which you want to get keys.

Responses

Status	Description
200 Success	Keys found.

Response Schema

api_keys: array

Array of associated Member and API Key objects.
- member: object
  
  Member object.
  - member_id: uuid
    
    Unique identifier of member.
  - email: string
    
    Email address of member.
  - first_name: string
    
    First name of member. If no first name exists, this item will not be returned.
  - last_name: string
    
    Last name of member. If no last name exists, this item will not be returned.
- api_key object
  
  API Key object.
  - api_key_id: uuid
    
    Unique identifier of API Key.
  - comment: string
    
    Comments associated with API Key.
  - scopes: array
    
    Array of scopes associated with API Key.
  - tags: array
    
    Array of tags associated with API Key. If no tags exist, this item will not be returned.
  - created: string
    
    Date and time when API Key was created.
  - expiration_date: string
    
    Date and time when API Key will expire. If no expiration date exists, this item will not be returned.

Endpoint

GET /projects/{project_id}/keys

Get Key

Retrieves basic information about the specified key. If the authenticated account has access to the members:read, admins:read, and owners:read project scopes, it will retrieve the information for any key in the project. Otherwise, it will retrieve the information for only one of the keys that belong to the authenticated account.

Required account/project scope(s): keys:read. Optional project scope(s): members:read, admins:read, owners:read.

Path Parameters

project_id: uuid

Unique identifier of the project for which you want to retrieve information.

key_id: uuid

Unique identifier of the key that you want to retrieve.

Responses

Status	Description
200 Success	Key found.
404 Not Found	A key with the specified key ID in the specified project was not found.

Response Schema

member: object

Member object.
- member_id: uuid
  
  Unique identifier of member.
- email: string
  
  Email address of member.
- first_name: string
  
  First name of member. If no first name exists, this item will not be returned.
- last_name: string
  
  Last name of member. If no last name exists, this item will not be returned.
api_key object

API Key object.
- api_key_id: uuid
  
  Unique identifier of API Key.
- comment: string
  
  Comments associated with API Key.
- scopes: array
  
  Array of scopes associated with API Key.
- tags: array
  
  Array of tags associated with API Key. If no tags exist, this item will not be returned.
- created: string
  
  Date and time when API Key was created.
- expiration_date: string
  
  Date and time when API Key will expire. If no expiration date exists, this item will not be returned.

Endpoint

GET /projects/{project_id}/keys/{key_id}

Create Key

Creates a new key in the specified project. You must create your first API Key using the Deepgram Console.

Required account/project scope(s): keys:write.

Path Parameters

project_id: uuid

Unique identifier of the project for which you want to create a key. Required.

Request Body Schema

comment: string

Comments associated with the key you would like to create. Must be between 1 and 128 characters long, not including whitespace. Required.

tags: array

Tags associated with the key you would like to create. Optional.

scopes: array

Scopes for the key you would like to create. Required.

Scopes cannot be empty.

The requested account scopes for the new key cannot exceed the scopes of the authenticated account making the request.

The requested project scopes for the new key cannot exceed the scopes of the authenticated account making the request.

expiration_date: datetime

Date on which the key you would like to create should expire. Optional.

If no time zone is specified, defaults to Coordinated Universal Time (UTC).

For each key, you may specify either an expiration_date or a time_to_live_in_seconds, but not both.

time_to_live_in_seconds: number

Length of time (in seconds) during which the key you would like to create will remain valid. Optional.

For each key, you may specify either an expiration_date or a time_to_live_in_seconds, but not both.

Responses

Status	Description
201 Success	Key created.

Response Schema

api_key_id: uuid

Unique identifier of the API Key.
key: string

Value of the API Key. This is the only chance to read the Key value; it cannot be recovered later.
comment: string

Comments associated with the API Key.
scopes: array

Project scopes associated with the API Key.
tags: array

Tags associated with the API Key. If no tags exist, this item will not be returned.
created: string

Date and time when the API Key was created.
expiration_date: string

Date and time when the API Key expires. If no expiration date exists, this item will not be returned.

Endpoint

POST /projects/{project_id}/keys

Delete Key

Deletes the specified key in the specified project. If the authenticated account has access to the members:write, admins:write, and owners:write project scopes, it will delete any key in the project. Otherwise, it will delete only keys belonging to the authenticated account.

Required account/project scope(s): keys:write. Optional project scope(s): members:write, admins:write, owners:write.

Path Parameters

project_id: uuid

Unique identifier of the project that contains the key that you want to delete.

key_id: uuid

Unique identifier of the key that you want to delete.

Responses

Status	Description
200 Success	Key deleted.

Response Schema

message: string

Message returned. Should read "Successfully deleted the API key!"

Endpoint

DELETE /projects/{project_id}/keys/{key_id}

Members

Members are users who have been given access to a specified Deepgram Project. Members are assigned Scopes, which determine what they can do in their assigned Project. Members can be assigned to multiple Projects and have different Scopes for each Project.

Get Members

Retrieves account objects for all of the accounts in the specified project.

Required account scope(s): project:read. Required project scope(s): project:read, members:read, admins:read, owners:read.

Path Parameters

project_id: uuid

Unique identifier of the project for which you want to get members.

Responses

Status	Description
200 Success	Members found.

Response Schema

members: array

Array of Members.
- member_id: uuid
  
  Unique identifier of member.
- first_name: string
  
  First name of member. Optional.
- last_name: string
  
  Last name of member. Optional.
- scopes: array
  
  Project scopes associated with member.
- email: string
  
  Email address of member.

Endpoint

GET /projects/{project_id}/members

Remove Member

Removes the specified account from the specified project. API keys created by this member for the specified project will also be deleted.

If the account being removed has scope member, then the requesting account must have scope members:write:kick. If the account being removed has scope admin, then the requesting account must have scope admins:write:kick. If the account being removed has scope owner, then the requesting account must have scope owners:write:kick. The account being removed must not be the sole account with the scope owner.

Required account scope(s): project:write. Required project scopes(s): members:write:kick or admins:write:kick or owners:write:kick.

Path Parameters

project_id: uuid

Unique identifier of the project that contains the account you want to remove.

member_id: uuid

Unique identifier of the account that you want to remove.

Responses

Status	Description
200 Success	Account removed.

Endpoint

DELETE /projects/{project_id}/members/{member_id}

Scopes

Scopes are permissions required to perform actions in a specified Deepgram Project. Scopes can be associated with Keys or Users. When associated with a Key, Scopes determine the actions that the Key can be used to perform in the Key's associated Project. When associated with a Member, Scopes determine what the user can do in their assigned Project. For more information, see Working with Roles.

Get Member Scopes

Lists the specified project scopes assigned to the specified member. If the authenticated account has access to the members:read:scopes, admins:read:scopes, and owners:read:scopes project scopes, it will retrieve project scopes for any member of the specified project. Otherwise, it will retrieve project scopes for only the authenticated account.

Required account scope(s): account:read, project:read. Required project scope(s): project:read. Optional project scope(s): members:read:scopes, admins:read:scopes, owners:read:scopes.

Path Parameters

project_id: uuid

Identifier of the project that contains the member for whom you want to get scopes.

member_id: uuid

Unique identifier of the member for whom you want to get scopes.

Responses

Status	Description
200 Success	Scopes found.

Response Schema

scopes: array

Array of scopes associated with the member.

Endpoint

GET /projects/{project_id}/members/{member_id}/scopes

Update Scope

Updates the specified project scopes assigned to the specified member.

If the specified member has the scope member or the scope being added is member, the requesting account must have the scope members:write:scopes. If the specified member has the scope admin or the scope being added is admin, the requesting account must have the scope admins:write:scopes. If the specified member has the scope owner or the scope being added is owner, the requesting account must have the scope owners:write:scopes.

If the scope being added is member, admin, or owner, it will replace the existing member, admin, or owner scope of the specified member unless the specified member is the only member with the owner scope. In this case, the request will fail.

If the scope being added is not member, admin, or owner, then the requesting account must also have the scope that it is trying to add to the specified member. For example, if the requesting account tries to add the project:write:settings project scope to a specified member, but the requesting account itself does not have the scope project:write:settings, then the request will fail.

Required account scope(s): project:write. Optional project scope(s): See the description.

Path Parameters

project_id: uuid

Unique identifier of the project that contains the specified member and scope that you want to update.

member_id: uuid

Unique identifier of the member for whom you want to update the scope.

Request Body Schema

scope: string

Scope for the specified member and project.

Responses

Status	Description
200 Success	Scope updated.

Response Schema

message: string

Success message.

Endpoint

PUT /projects/{project_id}/members/{member_id}/scopes

Invitations

To add a Member to a Deepgram Project, you can use the Deepgram Console or the Deepgram API to send an Invitation. When sending an Invitation, you provide an email address for the Member, and Deepgram generates an invitation link and emails it to them.

Leave Project

Removes the authenticated account from the specified project. Will also delete API Keys created by the account for the specified project. If the authenticated account is the only account on the project with the scope owner, the call will fail.

Required account scope(s): project:write.

Path Parameters

project_id: uuid

Unique identifier of the project from which you want to remove the authenticated account.

Responses

Status	Description
200 Success	Account removed from project.

Response Schema

message: string

Success message.

Endpoint

DELETE /projects/{project_id}/leave

Usage

Deepgram tracks requests made to Deepgram services and associates usage information with Projects.

Get All Requests

Generates a list of requests sent to the Deepgram API for the specified project over a given time range. Uses pagination to limit the number of results returned.

Path Parameters

project_id: uuid

Unique identifier of the project for which you want to retrieve requests.

Query Parameters

start: string

Start date of the requested date range. Format is YYYY-MM-DD. Defaults to the time of your first request.

If no time zone is specified, defaults to Coordinated Universal Time (UTC).

end: string

End date of the requested date range. Format is YYYY-MM-DD. Defaults to the current time.

If no time zone is specified, defaults to Coordinated Universal Time (UTC).

limit: integer

Number of results to return per page.

Default: 10

status: string

Status of requests to return. Enables you to filter requests depending on whether they have succeeded or failed. If not specified, returns requests with all statuses.

Default: null

Possible values: null, succeeded OR failed

Responses

Status	Description
200 Success	Requests found. Requests will be returned in descending order based on creation time (newest first).

Response Schema

page: integer

Page number that should be returned. Used for pagination.
limit: integer

Number of results to return per page. Used for pagination.
requests: array
- request_id: uuid
  
  Unique identifier of request.
- created: string
  
  Date/time when request was created.
- path: string
  
  Path of endpoint to which request was submitted.
- api_key_id: uuid
  
  Unique identifier of the API Key with which the request was submitted.
- response: object
  
  Response generated by the request. If a response has not yet been generated, this object will be empty.
  - details: object
    
    If the request failed, then this object will be replaced by an optional message field that may contain an error message.
    - usd: number
      
      Cost of the request in USD, if project is non-contract and the requesting account has appropriate permissions.
    - duration: number
      
      Length of time (in hours) of audio processed in the request.
    - total_audio: number
      
      Number of audio files processed in the request.
    - channels: integer
      
      Number of channels in the audio associated with the request.
    - streams: integer
      
      Number of audio streams associated with the request.
    - models: array
      
      Array of models applied when running the request.
    - method: string
      
      Processing method used when running the request.
    - tags: array
      
      Array of tags applied when running the request.
    - features: array
      
      Array of features used when running the request.
    - config: object
      
      Configuration used when running the request.
      - alternatives: integer
        
        Requested maximum number of transcript alternatives to return. If no alternative value was submitted, this item will not be returned.
      - diarize: boolean
        
        Indicates whether diarization was requested. If not requested, this item will not be returned.
      - keywords: array
        
        Array of keywords associated with the request. If no keywords were submitted, this item will not be returned.
      - language: string
        
        Language associated with the request. If no languages were submitted, this item will not be returned.
      - model: string
        
        Model associated with the request. If no models were submitted, this item will not be returned.
      - multichannel: boolean
        
        Indicates whether multichannel processing was requested. If not requested, this item will not be returned.
      - ner: boolean
        
        Indicates whether named-entity recognition (NER) was requested. If not requested, this item will not be returned.
      - numerals: boolean
        
        Indicates whether numeral conversion was requested. If not requested, this item will not be returned.
      - profanity_filter: boolean
        
        Indicates whether filtering profanity was requested. If not requested, this item will not be returned.
      - punctuate: boolean
        
        Indicates whether punctuation was requested. If not requested, this item will not be returned.
      - redact: array
        
        Indicates whether redaction was requested. If not requested, this item will not be returned.
      - search: array
        
        Array of seach terms associated with the request. If no search terms were submitted, this item will not be returned.
      - utterances: boolean
        
        Indicates whether utterance segmentation was requested. If not requested, this item will not be returned.
  - code: integer
  - completed: string
- callback: object
  
  Only exists if a callback was included in the request. If a callback was included in the request, but the request has not completed yet, then this object will exist, but it will be empty. The attempts item will exist only while the request has not completed. The completed item will exist only after the request completes.
  - attempts: integer
  - code: integer
  - completed: string

Endpoint

GET /projects/{project_id}/requests

Get Request

Retrieves the details of the specified request sent to the Deepgram API for the specified project.

Path Parameters

project_id: uuid

Unique identifier of the project for which you want to retrieve the specified request.

request_id: uuid

Unique identifier of the request that you want to retrieve.

Responses

Status	Description
200 Success	Request found.
404 Not Found	A request with the specified request ID in the specified project was not found.

Response Schema

request_id: uuid

Unique identifier of request.
created: string

Date and time when request was created.
path: string

Path of endpoint to which request was submitted.
api_key_id: uuid

Unique identifier of the API Key with which the request was submitted.
response: object

Response generated by the request. If a response has not yet been generated, this object will be empty.
- details: object
  
  If the request failed, then this object will be replaced by an optional message field that may contain an error message.
  - usd: number
    
    Cost of the request in USD, if project is non-contract and the requesting account has appropriate permissions.
  - duration: number
    
    Length of time (in hours) of audio processed in the request.
  - total_audio: number
    
    Number of audio files processed in the request.
  - channels: integer
    
    Number of channels in the audio associated with the request.
  - streams: integer
    
    Number of audio streams associated with the request.
  - models: array
    
    Array of models applied when running the request.
  - method: string
    
    Processing method used when running the request.
  - tags: array
    
    Array of tags applied when running the request.
  - features: array
    
    Array of features used when running the request.
  - config: object
    
    Configuration used when running the request.
    - alternatives: integer
      
      Requested maximum number of transcript alternatives to return. If no alternative value was submitted, this item will not be returned.
    - diarize: boolean
      
      Indicates whether diarization was requested. If not requested, this item will not be returned.
    - keywords: array
      
      Array of keywords associated with the request. If no keywords were submitted, this item will not be returned.
    - language: string
      
      Language associated with the request. If no languages were submitted, this item will not be returned.
    - model: string
      
      Model associated with the request. If no models were submitted, this item will not be returned.
    - multichannel: boolean
      
      Indicates whether multichannel processing was requested. If not requested, this item will not be returned.
    - ner: boolean
      
      Indicates whether named-entity recognition (NER) was requested. If not requested, this item will not be returned.
    - numerals: boolean
      
      Indicates whether numeral conversion was requested. If not requested, this item will not be returned.
    - profanity_filter: boolean
      
      Indicates whether filtering profanity was requested. If not requested, this item will not be returned.
    - punctuate: boolean
      
      Indicates whether punctuation was requested. If not requested, this item will not be returned.
    - redact: array
      
      Indicates whether redaction was requested. If not requested, this item will not be returned.
    - search: array
      
      Array of seach terms associated with the request. If no search terms were submitted, this item will not be returned.
    - utterances: boolean
      
      Indicates whether utterance segmentation was requested. If not requested, this item will not be returned.
- code: integer
- completed: string
callback: object

Only exists if a callback was included in the request. If a callback was included in the request, but the request has not been attempted yet, then this object will exist, but it will be empty. The attempts item will exist only while the request has not completed. The completed item will exist only after the request completes.
- attempts: integer
- code: integer
- completed: string

Endpoint

GET /projects/{project_id}/requests/{request_id}

Summarize Usage

Retrieves a summary of usage statistics. You can specify a date range.

Path Parameters

project_id: uuid

Unique identifier of the project for which you want to summarize usage.

Query Parameters

start: string

Start date of the requested date range. Format: YYYY-MM-DD. If a full timestamp is given, it will be truncated to a day. Dates are UTC. Defaults to the date of your first request.

end: string

End date of the requested date range. Format is YYYY-MM-DD. If a full timestamp is given, it will be truncated to a day. Dates are UTC. Defaults to the current date.

accessor: string

Limits results to requests made using the API key corresponding to the given accessor. If not specified, returns requests made using all API keys. To include multiple API Keys, send multiple instances in query string (e.g., accessor=2ed1307e-14f2-48a2-b996-97ea009cfa4e&accessor=1dc0296d-03e1-37z1-1885-86dz998bez3d).

tag: string

Limits results to requests associated with the specified tag. If not specified, returns requests with all tags. To include multiple tags, send multiple instances in query string (e.g., tag=dev&tag=production).

method: string

Limits results to requests processed using the specified method. If not specified, returns requests with all processing methods. To include multiple methods, send multiple instances in query string (e.g., method=sync&method=streaming).

Possible values include:

sync
async
streaming

Possible values: sync, async OR streaming

model: string

Limits results to requests run with the specified model UUID applied. If not specified, returns requests with all models. To include multiple models, send multiple instances in query string (e.g., model=4899aa60-f723-4517-9815-2042acc12a82&model=125125fb-e391-458e-a227-a60d6426f5d6).

multichannel: boolean

Limits results to requests that include the multichannel feature.

interim_results: boolean

Limits results to requests that include the interim_results feature.

punctuate: boolean

Limits results to requests that include the punctuate feature.

ner: boolean

Limits results to requests that include the ner feature.

utterances: boolean

Limits results to requests that include the utterances feature.

replace: boolean

Limits results to requests that include the replace feature.

profanity_filter: boolean

Limits results to requests that include the profanity_filter feature.

keywords: boolean

Limits results to requests that include the keywords feature.

diarize: boolean

Limits results to requests that include the diarize feature.

search: boolean

Limits results to requests that include the search feature.

redact: boolean

Limits results to requests that include the redact feature.

alternatives: boolean

Limits results to requests that include the alternatives feature.

numerals: boolean

Limits results to requests that include the numerals feature.

Responses

Status	Description
200 Success	Usage statistics found.
404 Not Found	Usage statistics for the requested date range in the specified project were not found.

Response Schema

start: string

Start date submitted for included requests.
end: string

End date submitted for included requests.
resolution: object
- units: string
  
  Units of resolution amount. For example, days.
- amount: integer
  
  Number of resolution units.
results: array

Array of Result objects, one for each day within the date range that has associated requests.
- start: string
  
  Start date of included requests.
- end: integer
  
  End date of included requests.
- hours: number
  
  Length of time (in hours) of audio submitted in included requests.
- total_hours: number
  
  Length of time (in hours) of audio processed in included requests. For example, if submitted audio is multichannel, total_hours processed will be greater than hours submitted because multiple channels are processed separately.
- requests: integer
  
  Number of included requests.

Endpoint

GET /projects/{project_id}/usage

Get Fields

Lists the features, models, tags, languages, and processing method used for requests in the specified project. You can specify a time range.

Path Parameters

project_id: uuid

Unique identifier of the project for which you want to retrieve fields.

Query Parameters

start: string

Start date of the requested date range. Format is YYYY-MM-DD. If a full timestamp is given, it will be truncated to a day. Dates are UTC.

Defaults to the date of your first request.

end: string

End date of the requested date range. Format is YYYY-MM-DD. If a full timestamp is given, it will be truncated to a day. Dates are UTC.

Defaults to the current date.

Responses

Status	Description
200 Success	Request fields found.

Response Schema

tags: array

Array of included tags.
models: array

Array of included models.
processing_methods: array

Array of processing methods.

Possible values: sync, async OR streaming
languages: array

Array of included languages.
features: array

Array of included features.

Possible values: multichannel, interim_results, punctuate, ner, utterances, replace, profanity_filter, keywords, diarize, search, redact, alternatives OR numerals

Endpoint

get /projects/{project_id}/usage/fields

Billing

Deepgram tracks individual transactions and transaction summaries for Deepgram services.

Get All Balances

Generates a list of outstanding balances for the specified project. To see balances, the authenticated account must be a project owner or administrator.

Path Parameters

project_id: uuid

Unique identifier of the project for which you want to retrieve outstanding balances.

Responses

Status	Description
200 success	Balances found.

Response Schema

balances: array

Array of balance objects.
- balance_id: uuid
  
  Unique identifier of the balance.
- amount: number
  
  Amount of the balance.
- units: string
  
  Units of the balance. May use usd or hour, depending on the project billing settings.
- purchase: string
  
  Unique identifier of the purchase order associated with the balance.

Endpoint

GET /projects/{project_id}/balances

Get Balance

Retrieves details about the specified balance. To see balances, the authenticated account must be a project owner or administrator.

Path Parameters

project_id: string

Unique identifier of the project for which you want to retrieve the specified balance.

balance_id: uuid

Unique identifier of the balance that you want to retrieve.

Responses

Status	Description
200 Success	Balance found.
404 Not Found	A balance with the specified balance ID in the specified project was not found.

Response Schema

balance_id: uuid

Unique identifier of the balance.
amount: number

Amount of the balance.
units: string

Units of the balance. May use usd or hour, depending on the project billing settings.
purchase: string

Unique identifier of the purchase order associated with the balance.

Endpoint

GET /projects/{project_id}/balances/{balance_id}

FEEDBACK

Did you find what you were looking for?