AI

Deepgram

Deepgram is a speech API: it turns recorded audio into text, and text into spoken audio with an Aura voice.

Authentication

  • API key

Actions

Generic API request. Call any Deepgram API endpoint on this connection, for the case where no shipped action covers it yet. The connection supplies the base URL, the authentication and the egress route, so only the path, query and body are yours to fill.

  • Get projectRetrieve a single Deepgram project by id (GET /projects/{projectid}).
  • Get project balancesList the outstanding balances for a Deepgram project (GET /projects/{projectid}/balances).
  • List modelsList the speech-to-text and text-to-speech models available to the API key, with each speech-to-text model's batch and streaming support and each voice's metadata (GET /models).
  • List project keysList the API keys for a Deepgram project (GET /projects/{projectid}/keys).
  • List projectsList the Deepgram projects the API key can access (GET /projects).
  • Text to speechSynthesize speech from text with a Deepgram Aura voice (POST /speak).
  • Text to speech (Streaming)Streaming sibling of Text to speech over Deepgram's speak WebSocket (wss /speak).
  • Transcribe audio fileTranscribe an audio file held in the blob store (POST /listen with the audio as the request body).
  • Transcribe audio URLTranscribe a pre-recorded audio file hosted at a public URL (POST /listen with a JSON body {url}).

Triggers

  • New project keyStarts when a new API key is created for the connected Deepgram project, detected by the key's created timestamp advancing past the stored cursor on each poll.

Product names, logos and brands are the property of their respective owners and are used here for identification only. Their use does not imply endorsement by, or affiliation with, those owners.