Gladia icon

Gladia

Speech-to-text API for transcribing, translating, and analyzing audio in real time.

1 trigger3 searches4 actionsPollingAuth: API key

AI-assisted documentation6 min read

This documentation is compiled from our integration source code, internal specs for Gladia, its official API documentation and anonymized requests logs we collect from our support team[2].

Open Gladia on WEXTL →

To use Gladia on WEXTL you need an active account and an API access token from your account settings.[3]

  1. Log in to your WEXTL account, add the Gladia node module to your workflow, and click Create new credential.
  2. Optional: In the Credential name field, enter a name for the credential.
  3. Enter the authentication credentials you copied from your Gladia account, or follow the on-screen instructions to create the credential.
  4. If prompted, authenticate your account and confirm access.
  5. If you want to make changes to your credential in the future, follow the steps in Manage credentials →
Connecting Gladia to WEXTL®
Video slide demonstrates how to integrate Gladia in the WEXTL visual workflow builder.[4]

Notes

Credentials are org-scoped; share them with teammates from the Credentials picker on any of its nodes.For detailed information on connecting an application, see Connect an application →

Watch TranscriptionsTrigger
Output fields[3]
FieldType
IDtext
Request IDtext
Versionnumber
Statustext
Created atdate
Completed atdate
Custom metadataobject
Error codenumber
Kindtext
Fileobject
IDtext
Filenametext
Sourcetext
Audio durationnumber
Number of channelsnumber
Request paramsobject
Context prompttext
Custom vocabularyboolean
Custom vocabulary configobject
Detect languageboolean
Enable code switchingboolean
Code switching configobject
Languagetext
Callback URLtext
Callbackboolean
Callback configobject
Resultobject
Metadataobject
Transcriptionobject
Translationobject
Summarizationobject
Moderationobject
Named entity recognitionobject
Name consistencyobject
Speaker reidentificationobject
Structured data extractionobject
Sentiment analysisobject
Get a Transcription Audio FileAction
Input fields[3]
FieldType
Transcription IDRequired
choice
Output fields[3]
FieldType
File Datatext
Get a Transcription ResultAction
Input fields[3]
FieldType
Transcription IDRequired
choice
Output fields[3]
FieldType
IDtext
Request IDtext
Versionnumber
Statustext
Created atdate
Completed atdate
Custom metadataobject
Error codenumber
Kindtext
Fileobject
IDtext
Filenametext
Sourcetext
Audio durationnumber
Number of channelsnumber
Request paramsobject
Context prompttext
Custom vocabularyboolean
Custom vocabulary configobject
Detect languageboolean
Enable code switchingboolean
Code switching configobject
Languagetext
Callback URLtext
Callbackboolean
Callback configobject
Resultobject
Metadataobject
Transcriptionobject
Translationobject
Summarizationobject
Moderationobject
Named entity recognitionobject
Name consistencyobject
Speaker reidentificationobject
Structured data extractionobject
Sentiment analysisobject
List TranscriptionsSearch
Input fields[3]
FieldType
Datedate
Before Datedate
After Datedate
Statusarray
Custom Metadataobject
Key NameRequired
text
ValueRequired
text
Limitnumber
Output fields[3]
FieldType
IDtext
Request IDtext
Versionnumber
Statustext
Created atdate
Completed atdate
Custom metadataobject
Error codenumber
Kindtext
Fileobject
IDtext
Filenametext
Sourcetext
Audio durationnumber
Number of channelsnumber
Request paramsobject
Context prompttext
Custom vocabularyboolean
Custom vocabulary configobject
Detect languageboolean
Enable code switchingboolean
Code switching configobject
Languagetext
Callback URLtext
Callbackboolean
Callback configobject
Resultobject
Metadataobject
Transcriptionobject
Translationobject
Summarizationobject
Moderationobject
Named entity recognitionobject
Name consistencyobject
Speaker reidentificationobject
Structured data extractionobject
Sentiment analysisobject
Create a TranscriptionAction
Input fields[3]
FieldType
Audio URLRequired
url
Custom Vocabularyboolean
Callbackboolean
Subtitlesboolean
Diarizationboolean
Translationboolean
Summarizationboolean
Moderationboolean
Named Entity Recognitionboolean
Chapterizationboolean
Names Consistencyboolean
Custom Spellingboolean
Custom Spelling Configarray
WordRequired
text
Spelling ValueRequired
array
Structured Data Extractionboolean
Structured Data Extraction Configobject
ClassesRequired
array
Sentiment Analysisboolean
Audio to LLMboolean
Audio to LLM Configobject
PromptsRequired
array
Custom Metadataarray
Key NameRequired
text
ValueRequired
text
Sentencesboolean
3other input fields
Output fields[3]
FieldType
IDtext
Result URLurl
Delete a TranscriptionAction
Input fields[3]
FieldType
Transcription IDRequired
choice
Make an API Calluniversal
Input fields[3]
FieldType
URLRequired
text
MethodRequired
choice
Headersarray
Headerobject
Query Stringarray
Parameterobject
Bodytext
Output fields[3]
FieldType
Bodytext
Headersobject
Status codenumber
Upload a FileAction
Input fields[3]
FieldType
AudioRequired
text
Output fields[3]
FieldType
Audio URLurl
Audio metadataobject
IDtext
Filenametext
Sourcetext
Extensiontext
Sizenumber
Audio durationnumber
Number of channelsnumber

Look for Gladia templates in the WEXTL template library.

Browse templates →
  1. WEXTL® Gladia Source Code connector implementation.
  2. Our users use cases and automations.
  3. Official API Documentation for Gladia.
  4. WEXTL® visual workflow builder data.

Last updated: Jul 24, 2026 18:11