> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Deepgram

> Deepgram provides AI-powered speech recognition and understanding services, offering APIs for real-time and pre-recorded audio transcription, text-to-speech, and audio intelligence.

![Deepgram logo](https://mintcdn.com/composio-preview/VNLruGH5mLZqXdPH/images/toolkits/deepgram.svg?fit=max\&auto=format\&n=VNLruGH5mLZqXdPH\&q=85\&s=37b82d4ab33155e60f2887f4bc308ccf)

* **Category:** audio & speech
* **Auth:** API\_KEY
* **Composio-managed OAuth available?** N/A
* **Tools:** 17
* **Triggers:** 0
* **Slug:** `DEEPGRAM`
* **Version:** 20261101\_00
* **Instant:** Supported on the latest version. Support varies by tool.

## Tools

> [accordion] Get Model by ID
>
> **Slug:** `DEEPGRAM_GET_MODEL`
>
> Retrieve metadata for a specific Deepgram model by its UUID. Returns detailed model information including name, architecture, supported languages, version, and capabilities. Works for both STT (speech-to-text) and TTS (text-to-speech) models.
>
> **Instant:** Supported on the latest version.
>
> **Instant pricing:** \$0 per request
>
> #### Input Parameters
>
> **model\_id** `string` *required*
>
> The specific UUID of the model to retrieve
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Public Models
>
> **Slug:** `DEEPGRAM_GET_MODELS`
>
> Retrieve metadata on all public Deepgram models (speech-to-text and text-to-speech). Returns comprehensive model information including supported languages, architectures, versions, and capabilities. Set include\_outdated to True to include deprecated versions.
>
> **Instant:** Supported on the latest version.
>
> **Instant pricing:** \$0 per request
>
> #### Input Parameters
>
> **include\_outdated** `boolean`
>
> If true, include all versions of every model; otherwise only the latest.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Project Balance
>
> **Slug:** `DEEPGRAM_GET_PROJECT_BALANCE`
>
> Retrieve one balance for a Deepgram project in its native units.
>
> #### Input Parameters
>
> **balance\_id** `string` *required*
>
> Unique identifier of the project balance
>
> **project\_id** `string` *required*
>
> Unique identifier of the Deepgram project
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Project Billing Breakdown
>
> **Slug:** `DEEPGRAM_GET_PROJECT_BILLING_BREAKDOWN`
>
> Get a project's billing breakdown for an optional date range, preserving provider-reported amounts and units.
>
> #### Input Parameters
>
> **end** `string`
>
> End of the billing range in YYYY-MM-DD or ISO 8601 format.
>
> **start** `string`
>
> Start of the billing range in YYYY-MM-DD or ISO 8601 format.
>
> **project\_id** `string` *required*
>
> Unique identifier of the Deepgram project.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Project Request
>
> **Slug:** `DEEPGRAM_GET_PROJECT_REQUEST`
>
> Retrieve one request log for a Deepgram project by ID.
>
> #### Input Parameters
>
> **project\_id** `string` *required*
>
> Unique identifier of the Deepgram project.
>
> **request\_id** `string` *required*
>
> Unique identifier of the project request log.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Deepgram Projects
>
> **Slug:** `DEEPGRAM_GET_PROJECTS`
>
> List Deepgram projects accessible to the API key. Projects missing an ID or name are omitted from the returned list.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Project Usage Breakdown
>
> **Slug:** `DEEPGRAM_GET_PROJECT_USAGE_BREAKDOWN`
>
> Get project usage grouped by provider usage fields, preserving native units.
>
> #### Input Parameters
>
> **end** `string`
>
> End of the usage range in YYYY-MM-DD or ISO 8601 format.
>
> **start** `string`
>
> Start of the usage range in YYYY-MM-DD or ISO 8601 format.
>
> **project\_id** `string` *required*
>
> Unique identifier of the Deepgram project.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Project Usage Summary
>
> **Slug:** `DEEPGRAM_GET_PROJECT_USAGE_SUMMARY`
>
> Retrieve aggregated project usage statistics, including speech durations, requests, channels, confidence and relevance, with usage breakdowns by model, accessor and tag. A 404 response is returned as an all-zero summary with an empty breakdown.
>
> #### Input Parameters
>
> **end** `string`
>
> End date for the usage summary range. Accepts YYYY-MM-DD or ISO 8601 format (e.g., '2024-01-31' or '2024-01-31T23:59:59Z')
>
> **tag** `string`
>
> Filter usage by request tag. Returns only usage from requests tagged with this value
>
> **model** `string`
>
> Filter usage by Deepgram model name (e.g., 'nova-2', 'general', 'whisper'). Returns only usage from requests that used this model
>
> **start** `string`
>
> Start date for the usage summary range. Accepts YYYY-MM-DD or ISO 8601 format (e.g., '2024-01-01' or '2024-01-01T00:00:00Z')
>
> **project\_id** `string` *required*
>
> Unique identifier of the Deepgram project
>
> **accessor\_id** `string`
>
> Filter usage by API key or user accessor ID. Returns only usage attributed to this specific accessor
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Project Balances
>
> **Slug:** `DEEPGRAM_LIST_PROJECT_BALANCES`
>
> List all balances for a Deepgram project without converting their native amounts or units.
>
> #### Input Parameters
>
> **project\_id** `string` *required*
>
> Unique identifier of the Deepgram project whose balances to list.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Project Billing Fields
>
> **Slug:** `DEEPGRAM_LIST_PROJECT_BILLING_FIELDS`
>
> Return the fields available for project billing breakdowns.
>
> #### Input Parameters
>
> **end** `string`
>
> End of the billing range in YYYY-MM-DD or ISO 8601 format.
>
> **start** `string`
>
> Start of the billing range in YYYY-MM-DD or ISO 8601 format.
>
> **project\_id** `string` *required*
>
> Unique identifier of the Deepgram project.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Project Purchases
>
> **Slug:** `DEEPGRAM_LIST_PROJECT_PURCHASES`
>
> List purchases for a Deepgram project without converting native values.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Maximum number of purchases to return.
>
> **project\_id** `string` *required*
>
> Unique identifier of the Deepgram project.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Project Requests
>
> **Slug:** `DEEPGRAM_LIST_PROJECT_REQUESTS`
>
> List request logs for a Deepgram project with date and page controls.
>
> #### Input Parameters
>
> **end** `string`
>
> End of the request-log range in ISO 8601 format.
>
> **page** `integer`
>
> Zero-based page number to retrieve.
>
> **limit** `integer`
>
> Maximum number of request logs to return.
>
> **start** `string`
>
> Start of the request-log range in ISO 8601 format.
>
> **project\_id** `string` *required*
>
> Unique identifier of the Deepgram project.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Project Scopes
>
> **Slug:** `DEEPGRAM_LIST_PROJECT_SCOPES`
>
> Return a static list of Deepgram permission scope types and their descriptions. The list is the same for every supplied project ID.
>
> #### Input Parameters
>
> **project\_id** `string` *required*
>
> Unique identifier of the Deepgram project to list scopes for.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Project Usage Fields
>
> **Slug:** `DEEPGRAM_LIST_PROJECT_USAGE_FIELDS`
>
> Return the fields available for project usage breakdowns.
>
> #### Input Parameters
>
> **end** `string`
>
> End of the usage range in YYYY-MM-DD or ISO 8601 format.
>
> **start** `string`
>
> Start of the usage range in YYYY-MM-DD or ISO 8601 format.
>
> **project\_id** `string` *required*
>
> Unique identifier of the Deepgram project.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Think Models
>
> **Slug:** `DEEPGRAM_LIST_THINK_MODELS`
>
> Tool to list available think models for AI agent processing and voice agent configuration. Use when you need to see which think models are available for voice agents.
>
> **Instant:** Supported on the latest version.
>
> **Instant pricing:** \$0 per request
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Transcribe Pre-recorded Audio
>
> **Slug:** `DEEPGRAM_SPEECH_TO_TEXT_PRE_RECORDED`
>
> Transcribe pre-recorded audio from a publicly accessible URL, returning the primary transcript in the first channel and alternative. Managed access is limited to Nova-3 English mono PCM WAV audio up to 60 seconds and 8 MiB, without paid add-ons; other options require a Deepgram account.
>
> **Instant:** Supported on the latest version.
>
> **Instant pricing:** \$0.004 per audio minute for prerecorded Nova-3 English transcription
>
> **Discount:** 10
>
> #### Input Parameters
>
> **tier** `string`
>
> Enhanced tier for higher-accuracy recognition. Requires your own Deepgram key.
>
> **model** `string`
>
> Deepgram model to use (e.g., 'nova-3', 'general', 'phonecall'). Without your own Deepgram key, only 'nova-3' is supported and is used when omitted.
>
> **diarize** `boolean`
>
> Enable speaker diarization if true. Requires your own Deepgram key.
>
> **keyterm** `array`
>
> List of keyterms to boost in the transcript. Supported by Nova-3 and Flux models only. Use simple terms without intensifiers (e.g., 'invoice', 'payment terms'). For other models, use 'keywords' instead. Requires your own Deepgram key.
>
> **version** `string`
>
> Specific model version to use. Requires your own Deepgram key.
>
> **keywords** `array`
>
> List of keywords to boost in the transcript. Supported by Nova-2, Nova-1, Enhanced, and Base models. Format: 'keyword:intensifier' (e.g., 'invoice:5'). For Nova-3 or Flux models, use 'keyterm' instead. Requires your own Deepgram key.
>
> **language** `string`
>
> Language code for transcription (e.g., 'en-US'). Without your own Deepgram key, only 'en' or 'en-US' is supported and 'en' is used when omitted.
>
> **audio\_url** `string` *required*
>
> Public URL of the audio file to transcribe. Must be a direct, publicly downloadable media file URL — not a preview page, auth-gated link, or expiring/short-lived URL.
>
> **punctuate** `boolean`
>
> Automatically punctuate transcript.
>
> **alternatives** `integer`
>
> Number of alternative transcripts to return.
>
> **content\_type** `string ("audio/wav" | "audio/mp3" | "audio/mpeg" | "audio/flac" | "audio/webm")` *required*
>
> MIME type of the audio file. Without your own Deepgram key, only 'audio/wav' is supported.
>
> **smart\_format** `boolean`
>
> Apply smart formatting (capitalization/punctuation).
>
> **detect\_language** `boolean`
>
> Automatically detect language if true. Prefer explicit `language` over this when the audio language is known; auto-detection reduces accuracy for non-English content. Requires your own Deepgram key.
>
> **interim\_results** `boolean`
>
> Return interim results if true. Requires your own Deepgram key.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Text-to-Speech (REST)
>
> **Slug:** `DEEPGRAM_TEXT_TO_SPEECH_REST`
>
> Convert text to speech and return base64-encoded audio with its content type. Managed access uses Aura-2 Thalia English and accepts up to 1,000 characters without voice, version, language, speed or pitch overrides.
>
> **Instant:** Supported on the latest version.
>
> **Instant pricing:** \$0.03 per 1,000 Aura-2 characters
>
> **Discount:** 10
>
> #### Input Parameters
>
> **text** `string` *required*
>
> The text to be synthesized into speech.
>
> **model** `string`
>
> Deepgram TTS model to use (e.g., 'aura-2-thalia-en'). Without your own Deepgram key, only 'aura-2-thalia-en' is supported and is used when omitted; other models such as 'aura-asteria-en' need your own Deepgram key.
>
> **pitch** `number`
>
> Pitch adjustment multiplier (0.5–2.0).
>
> **speed** `number`
>
> Speech rate multiplier (0.25–4.0).
>
> **voice** `string`
>
> Desired voice within the selected model.
>
> **version** `string`
>
> Model version identifier.
>
> **encoding** `string`
>
> Audio encoding type (e.g., 'linear16', 'mp3').
>
> **language** `string`
>
> Language code for synthesis (e.g., 'en-US').
>
> **container** `string`
>
> Container format for audio (e.g., 'wav', 'mp3').
>
> **sample\_rate** `integer`
>
> Desired sample rate for output audio in Hz (e.g., 16000).
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not
