About this integration
Speech-to-text API for transcribing, translating, and analyzing audio in real time. Use it from the workflow canvas with no custom glue script required.
This integration exposes 1 trigger, 3 search modules and 4 actions as workflow nodes. Authentication uses basic authentication.
How to connect
The credential form asks for API Key.
Prefer the interactive builder form? Open it on the app page.
Paste your credentials once — WEXTL® stores them encrypted and reuses the connection across every workflow that needs it.
Enter your credentials below. WEXTL stores them encrypted and uses them only to call the API on your behalf.
Connecting Gladia to WEXTL®
| Field | Type | Help |
|---|---|---|
API KeyRequired | password | On Gladia website go to the API keys section to grab your API Key. |
Use it in workflow automation
Start with Watch Transcriptions, then add Create a Transcription.
The canvas below runs Watch Transcriptions into Create a Transcription — watch the video, then drop a node onto the canvas.
Select the Watch Transcriptions trigger and the workflow fires automatically when the event occurs — no polling required.
Then add Delete a Transcription as the next node. Branch, filter, or hand off to other integrations from there.
The integration includes 5 ready-made modules for developer tools work — each run logs its inputs and outputs for debugging.
Gladia workflow on the canvas: Watch Transcriptions then Delete a Transcription
Triggers, searches and actions
Use the tables below to inspect Gladia's 1 trigger, 3 search modules, and 4 actions.
Triggers
1 trigger fire automatically when specified events occur — no polling or cron job needed.
- Watch Transcriptions
Searches
Fetch data on demand using 3 search modules that query the app during a run.
- Get a Transcription Audio File
- Get a Transcription Result
- List Transcriptions
Actions
4 action modules cover the full range of create, update, and delete operations.
- Create a Transcription
- Delete a Transcription
- Make an API Call
- Upload a File
Explore the fields available for each Gladia trigger, search, and action.
Triggers
| Field | Type |
|---|---|
ID | text |
Request ID | text |
Version | number |
Status | text |
Created at | date |
Completed at | date |
Custom metadata | object |
Error code | number |
Kind | text |
File | object |
ID | text |
Filename | text |
Source | text |
Audio duration | number |
Number of channels | number |
Request params | object |
Context prompt | text |
Custom vocabulary | boolean |
Custom vocabulary config | object |
Detect language | boolean |
Enable code switching | boolean |
Code switching config | object |
Language | text |
Callback URL | text |
Callback | boolean |
Callback config | object |
Result | object |
Metadata | object |
Transcription | object |
Translation | object |
Summarization | object |
Moderation | object |
Named entity recognition | object |
Name consistency | object |
Speaker reidentification | object |
Structured data extraction | object |
Sentiment analysis | object |
Searches
| Field | Type |
|---|---|
Transcription IDRequired | choice |
| Field | Type |
|---|---|
File Data | text |
| Field | Type |
|---|---|
Transcription IDRequired | choice |
| Field | Type |
|---|---|
ID | text |
Request ID | text |
Version | number |
Status | text |
Created at | date |
Completed at | date |
Custom metadata | object |
Error code | number |
Kind | text |
File | object |
ID | text |
Filename | text |
Source | text |
Audio duration | number |
Number of channels | number |
Request params | object |
Context prompt | text |
Custom vocabulary | boolean |
Custom vocabulary config | object |
Detect language | boolean |
Enable code switching | boolean |
Code switching config | object |
Language | text |
Callback URL | text |
Callback | boolean |
Callback config | object |
Result | object |
Metadata | object |
Transcription | object |
Translation | object |
Summarization | object |
Moderation | object |
Named entity recognition | object |
Name consistency | object |
Speaker reidentification | object |
Structured data extraction | object |
Sentiment analysis | object |
| Field | Type |
|---|---|
Date | date |
Before Date | date |
After Date | date |
Status | array |
Custom Metadata | object |
Key NameRequired | text |
ValueRequired | text |
Limit | number |
| Field | Type |
|---|---|
ID | text |
Request ID | text |
Version | number |
Status | text |
Created at | date |
Completed at | date |
Custom metadata | object |
Error code | number |
Kind | text |
File | object |
ID | text |
Filename | text |
Source | text |
Audio duration | number |
Number of channels | number |
Request params | object |
Context prompt | text |
Custom vocabulary | boolean |
Custom vocabulary config | object |
Detect language | boolean |
Enable code switching | boolean |
Code switching config | object |
Language | text |
Callback URL | text |
Callback | boolean |
Callback config | object |
Result | object |
Metadata | object |
Transcription | object |
Translation | object |
Summarization | object |
Moderation | object |
Named entity recognition | object |
Name consistency | object |
Speaker reidentification | object |
Structured data extraction | object |
Sentiment analysis | object |
Actions
| Field | Type |
|---|---|
Audio URLRequired | url |
Custom Vocabulary | boolean |
Callback | boolean |
Subtitles | boolean |
Diarization | boolean |
Translation | boolean |
Summarization | boolean |
Moderation | boolean |
Named Entity Recognition | boolean |
Chapterization | boolean |
Names Consistency | boolean |
Custom Spelling | boolean |
Custom Spelling Config | array |
WordRequired | text |
Spelling ValueRequired | array |
Structured Data Extraction | boolean |
Structured Data Extraction Config | object |
ClassesRequired | array |
Sentiment Analysis | boolean |
Audio to LLM | boolean |
Audio to LLM Config | object |
PromptsRequired | array |
Custom Metadata | array |
Key NameRequired | text |
ValueRequired | text |
Sentences | boolean |
| Field | Type |
|---|---|
ID | text |
Result URL | url |
| Field | Type |
|---|---|
Transcription IDRequired | choice |
| Field | Type |
|---|---|
URLRequired | text |
MethodRequired | choice |
Headers | array |
Header | object |
Query String | array |
Parameter | object |
Body | text |
| Field | Type |
|---|---|
Body | text |
Headers | object |
Status code | number |
| Field | Type |
|---|---|
AudioRequired | text |
| Field | Type |
|---|---|
Audio URL | url |
Audio metadata | object |
ID | text |
Filename | text |
Source | text |
Extension | text |
Size | number |
Audio duration | number |
Number of channels | number |



