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
  • Response
  • Special Considerations
  • White Space or Special Characters
  • Apply Multiple Instances
  • Comparison to Tagging
Results Processing

Extra Metadata

Extra Metadata allows you to label your requests for the purpose of identification in downstream processing.
Was this page helpful?
Previous

Migrating From Amazon Web Services (AWS) Transcribe to Deepgram

Learn how to migrate from Amazon Web Services (AWS) Transcribe to Deepgram. For developers who are using AWS Transcribe and and want to migrate to Deepgram.

Next
Built with

extra string

Pre-recorded Streaming:NovaStreaming: Flux All available languages

Deepgram’s Extra Metadata feature allows you to attach arbitrary key-value pairs to your API requests that are attached to the API response for usage in downstream processing.

Extra metadata is limited to 2048 characters per key-value pair.

Enable Feature

To enable Extra Metadata, when you call Deepgram’s API, add an extra parameter in the query string and pass a key-value pair you would like to include in the response.

extra=KEY:VALUE

To transcribe audio from a file on your computer, run the following cURL command in a terminal or your favorite API client.

cURL
$curl \
> --request POST \
> --header 'Authorization: Token YOUR_DEEPGRAM_API_KEY' \
> --data-binary @youraudio.wav \
> --url 'https://api.deepgram.com/v1/listen?extra=KEY:VALUE'

Replace YOUR_DEEPGRAM_API_KEY with your Deepgram API Key.

Response

If you included extra=myKey:someValue in your request, the key-value pair would be passed through to the response in the following format:

JSON
1{
2 "metadata": {
3 "extra": {
4 "myKey": "someValue"
5 }
6 ...
7 }
8 ...
9}

Special Considerations

White Space or Special Characters

If your extra metadata includes spaces or special characters, be sure to URL encode it:

extra=dataflow:marketing%20team or extra=dataflow:marketing+team

Apply Multiple Instances

To apply multiple extra key-value pairs, submit the query parameter multiple times in your API request:

extra=team:marketing&extra=purpose:legal

If your request contains multiple instances of extra with the same key, the corresponding values will not be merged. Instead, the last value will overwrite any previous values.

For example, extra=team:marketing&extra=team:gtm will return "extra": { "team": "gtm" } in the response.

Comparison to Tagging

Tagging is a similar feature to Extra Metadata. Where Extra Metadata is primarily intended for passing data to downstream processing steps, Tagging is useful for tracking and filtering usage.

Below is a comparison table summarizing the main differences between the two features:

Extra MetadataTagging
Primarily for passing data to downstream processing steps✅❌
Primarily for tracking usage❌✅
Configurable per request✅✅
Configurable per API key❌✅
Character limit per value2048 chars128 chars
Can be used to filter usage❌✅
Can specify a key in a key-value pair✅❌
Can specify a value in a key-value pair✅✅