supermarket

Transcribe audio

Deepgram

Speech-to-text API that transcribes recorded or live audio into text with word timings and optional speaker labels.

At a glance

Provider
Deepgram
Category
Transcribe audio
Type
Hosted API
Pricing model
Pay as you go from prepaid credit; Growth plan from $4,000 a year1
Free tier
$200 credit that does not expire, no card1
Authentication
API key in Authorization: Token header; temporary JWT12
Connect via
REST API, WebSocket, SDKs, dg CLI with MCP server, docs MCP server9
Read from the provider's pages
2026-11-04
Pricing
  • Pricing model: Pay as you go against prepaid credit; Growth plan from $4,000 a year in prepaid credits; Enterprise is custom
  • Free tier: $200 credit, does not expire (about 43,000 minutes of Nova-3)
  • Card required for free tier: No
Pricing in full →Tools
  • Official MCP server: Yes, remote and local
  • Address or package: dg mcp (stdio, built into the dg CLI; the CLI also offers dg mcp --transport sse --port 8000); remote docs server at https://api.dx.deepgram.com/kapa/mcp
  • Remote server scope: Documentation search only; returned HTTP 401 with an OAuth challenge when sent initialize without credentials
Tools in full →Authentication
  • Who creates the account: A person signs up in the Console; whether an agent can sign up alone is not stated
  • Where to get a key: Deepgram Console (console.deepgram.com) or the Deepgram API
  • Other requirements: None stated for the free credit; no credit card needed to start
Authentication in full →Setup
  • REST API: https://api.deepgram.com/v1/listen; regional hosts api.eu.deepgram.com, api.au.deepgram.com, api.in.deepgram.com
  • MCP server: dg mcp (local, stdio); https://api.dx.deepgram.com/kapa/mcp (remote, docs only)
  • OpenAPI spec: https://developers.deepgram.com/openapi.json
Setup in full →Limits
  • Concurrent pre-recorded requests: 50 per project for Nova-3, Nova-2, Nova, Enhanced and Base (Pay as you go and Growth)
  • Concurrent pre-recorded requests (other page): 100 per project for Nova, Base and Enhanced
  • Concurrent streaming connections: 150 on Pay as you go, 225 on Growth (North America); Enterprise set to peak traffic
Limits in full →Privacy
  • Data location: Global endpoint api.deepgram.com by default; regional endpoints for EU, Australia and India keep processing and storage in-region
  • Retention: By default audio and transcripts are retained to improve models; with mip_opt_out=true only for the time needed to process the request. Usage logs: 90 days
  • Used for training: Yes by default through the Model Improvement Program; opt out per request with mip_opt_out=true
Privacy in full →

Read from Deepgram’s own pages on 2026-11-04. Every number links to the page a value came from. For agents, the same facts as markdown: /tools/transcribe-audio/deepgram.md