For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Ask AIPlaygroundLoginFree API Key
HomeAPI ReferenceVoice AgentSpeech-to-TextText-to-SpeechIntelligenceSelf-Hosted Deployments
HomeAPI ReferenceVoice AgentSpeech-to-TextText-to-SpeechIntelligenceSelf-Hosted Deployments
    • Getting Started with Speech to Text
  • Pre-Recorded Audio
    • Getting Started
    • Feature Overview
    • Template Apps
  • Streaming Audio
    • Compare Flux to Nova-3
  • Models and Languages
    • Models & Languages Overview
    • Languages Support
    • Language Detection
    • Multilingual Codeswitching
    • Model Options
    • Version
  • Formatting
    • Speaker Diarization
    • Dictation
    • Filler Words
    • Measurements
    • Numerals
    • Paragraphs
    • Profanity Filtering
    • Punctuation
    • Redaction
    • Smart Formatting
    • Supported Entity Types
    • Utterances
    • Utterance Split
  • Custom Vocabulary
    • Find and Replace
    • Keyterm Prompting
    • Keywords
    • Search
  • Media Input Settings
    • Channels
    • Encoding
    • Multichannel
    • Sample Rate
  • Results Processing
    • Understanding Word Confidence Scores
    • STT Callback
    • STT Tagging
    • Extra Metadata
  • Migrating
    • Migrating From Amazon Web Services (AWS) Transcribe to Deepgram
    • Migrating From Google Speech-to-Text (STT) to Deepgram
    • Migrating From OpenAI Whisper to Deepgram
    • Migrating from AssemblyAI Speech-to-Text to Deepgram
LogoLogo
Ask AIPlaygroundLoginFree API Key
On this page
  • Enable Feature
  • Use the Latest Version
  • Use an Earlier Version of a Standard Model
  • Use a Specific Version of a Custom Trained Model
  • Get Early Access to an Updated Standard Model
  • When to use Versions
Models and Languages

Version

Version allows you to specify the version of the model you want to use to process your submitted audio.
Was this page helpful?
Previous

Speaker Diarization

Diarize recognizes speaker changes and assigns a speaker to each word in the transcript.
Next
Built with

version string Default: latest

Pre-recorded Streaming:Nova

Deepgram’s Version feature allows you to specify the version of the model you want to use to process your submitted audio.

Enable Feature

To enable Version, when you call Deepgram’s API, add a version parameter in the query string and set it to the version of the model you want to use to process your submitted audio.

version=MODEL_VERSION

Use the Latest Version

To use the latest version of your selected model, send latest in the version parameter:

version=latest

Use an Earlier Version of a Standard Model

To use an earlier version of a selected Deepgram standard model, send the version number in the version parameter:

version=VERSION_NUMBER

Example: version=2021-03-17.0

You can locate version numbers of Deepgram standard models in our changelog. Select Speech Model to filter the updates.

Use a Specific Version of a Custom Trained Model

To use a specific version of a custom model associated with your account, send the custom model’s version_id in the version parameter:

version=VERSION_ID

Example: version=12345678-1234-1234-1234-1234567890ab

Get Early Access to an Updated Standard Model

When we release updated versions of Deepgram standard models, you may be able to try them out and provide feedback. To do so, send the version name of the selected model in the version parameter:

version=VERSION_NAME

Example: version=beta

To learn about updated model availability and get relevant version names, contact Support.

When to use Versions

  • If you want to make sure you are using the latest version of a Deepgram model.
  • If you want to use an earlier version of a Deepgram model.
  • If you want to use a specific version of a custom Deepgram model.