- 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
Get Model by ID
Get Model by ID
Slug:
DEEPGRAM_GET_MODELRetrieve 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 requestInput Parameters
Output
Get Public Models
Get Public Models
Slug:
DEEPGRAM_GET_MODELSRetrieve 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 requestInput Parameters
Output
Get Project Balance
Get Project Balance
Get Project Billing Breakdown
Get Project Billing Breakdown
Get Project Request
Get Project Request
List Deepgram Projects
List Deepgram Projects
Get Project Usage Breakdown
Get Project Usage Breakdown
Get Project Usage Summary
Get Project Usage Summary
Slug:
DEEPGRAM_GET_PROJECT_USAGE_SUMMARYRetrieve 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 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’)
Filter usage by Deepgram model name (e.g., ‘nova-2’, ‘general’, ‘whisper’). Returns only usage from requests that used this model
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’)
Filter usage by API key or user accessor ID. Returns only usage attributed to this specific accessor
Output
List Project Balances
List Project Balances
List Project Billing Fields
List Project Billing Fields
List Project Purchases
List Project Purchases
List Project Requests
List Project Requests
List Project Scopes
List Project Scopes
List Project Usage Fields
List Project Usage Fields
List Think Models
List Think Models
Transcribe Pre-recorded Audio
Transcribe Pre-recorded Audio
Slug:
DEEPGRAM_SPEECH_TO_TEXT_PRE_RECORDEDTranscribe 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 transcriptionDiscount: 10Input Parameters
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.
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.
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 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.
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.
MIME type of the audio file. Without your own Deepgram key, only ‘audio/wav’ is supported.
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.Output
Text-to-Speech (REST)
Text-to-Speech (REST)
Slug:
DEEPGRAM_TEXT_TO_SPEECH_RESTConvert 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 charactersDiscount: 10Input Parameters
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.