Jump to Content
Deepgram Docs
DocumentationAPI ReferencePlaygroundCommunityBlogStatus
v1.0

Free API KeyDeepgram Docs
Free API Key
v1.0DocumentationAPI ReferencePlaygroundCommunityBlogStatus

Deepgram Docs

  • Introduction
  • Support

Getting Started

  • Pre-Recorded Audio Quickstart
  • Live Streaming Audio Quickstart
  • Nova Quickstart
  • DG Whisper Cloud Quickstart
  • Starter Apps

Guides

  • Fundamentals
    • Authenticating
    • Managing Projects
    • Using Multiple Projects
    • Working with Roles
    • Supported Audio Formats
    • Deployment Options
    • Create Additional API Keys
  • Tips and Tricks
    • Transcribing Pre-recorded Audio
    • Generating and Saving Transcripts From the Terminal
    • Determining Your Audio Format for Live Streaming Audio
    • Getting Started With the Streaming Test Suite
    • Using Callbacks to Return Transcripts to Your Server
    • Automatically Generating WebVTT and SRT Captions
    • Automatically Transcribing and Summarizing Phone Calls
    • Measuring Streaming Latency
  • Migrating
    • Migrating from Amazon Web Services (AWS) Transcribe to Deepgram
    • Migrating from Google Speech-to-Text (STT) to Deepgram
  • Feature Deep Dives
    • Understanding When to Use the Multichannel and Diarization Features
    • Understanding When to Use the Keywords and Search Features
    • Understanding Endpointing and Interim Results When Transcribing Live Streaming Audio
  • Troubleshooting
    • Recovering from Connection Errors and Timeouts When Live Streaming Audio
    • WebSocket DATA and NET Errors When Live Streaming Audio
    • Callback Not Recieved
  • Use Cases
    • Calculate Talk Time Analytics
    • Transcribe Meetings in Realtime
    • Transcribe Recorded Calls with Twilio
  • Integrations
    • On-premise Twilio Integration
    • Integrate Deepgram with Zoom

Features

  • Features Overview

MOdel Selection

  • Language
  • Model
  • Tier
  • Version

ConvERT

  • Smart Formatting
  • Diarization
  • Find and Replace
  • Keywords
  • Numerals
  • Paragraphs
  • Profanity Filtering
  • Punctuation
  • Redaction
  • Utterances
  • Utterance Split

Classify

  • Language Detection

Distill

  • Entity Detection
  • Summarization
  • Topic Detection

RetriEVE

  • Search

media input

  • Channels
  • Encoding
  • Multichannel
  • Sample Rate

RESULT PROCESSING

  • Callback
  • Endpointing
  • Interim Results
  • Tagging

SDKS

  • Deepgram SDKs
  • Node SDK
    • Pre-Recorded Audio Transcription
    • Live Streaming Audio Transcription
    • Projects
    • Keys
    • Usage
    • Billing
    • Members
    • Scopes
    • Invitations
  • Python SDK
    • Pre-Recorded Audio Transcription
    • Live Streaming Audio Transcription
    • Projects
    • Keys
    • Usage
    • Billing
    • Members
    • Scopes
    • Invitations
  • .NET SDK
    • Configuration
    • Logging
    • Pre-Recorded Audio Transcription
    • Live Streaming Audio Transcription
    • Projects
    • Keys
    • Usage
  • Deno SDK [community]
  • Go SDK [community]
  • Rust SDK [community]

On-premises deployments

  • Getting Started
    • On-Prem Introduction
    • Designing Your Architecture
    • Configuring Your Environment
    • Licensing
  • Configure Your Deployment Environment
    • AWS
    • Bare-Metal Servers
  • Deploy Deepgram On-Prem
    • Ubuntu 20.04 LTS
    • RHEL 7
    • RHEL 8
    • Maintaining
    • Autoscaling Best Practices
  • On-Prem Add-ons
    • Introduction
    • License Proxy
    • Metrics Guide
    • Prometheus Integration
    • Deepgram UniMRCP Plugin
    • DGTools

Security

  • Security Policy
  • Data Privacy Compliance
  • Information Security & Privacy Statement

Support

Suggest Edits

Support is now available through the Deepgram community.

If you have a specific support contract, you can find details and links to contact us for support on your Console dashboard.

Updated 18 days ago