About this integration
Generates realistic text-to-speech and speech-to-text audio using AI voice models. Use it from the workflow canvas with no custom glue script required.
This integration exposes 0 triggers, 0 search modules and 3 actions as workflow nodes. Authentication uses basic authentication.
This is a focused integration — 3 public modules. The field tables below are the full reference. Connecting it uses API Key.
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 Fish Audio to WEXTL®
| Field | Type | Help |
|---|---|---|
API KeyRequired | password | You can obtain your API Key in Dashboard Settings. |
Use it in workflow automation
Add Create Speech to Text as a workflow step.
The canvas below shows the integration — watch the video, then drop a node onto the canvas.
Start with the Create Speech to Text step and run it on demand or on a schedule.
Then add Make an API Call as the next node. Branch, filter, or hand off to other integrations from there.
The integration includes 3 ready-made modules for AI work — each run logs its inputs and outputs for debugging.
Fish Audio workflow on the canvas: Create Speech to Text then Make an API Call
Triggers, searches and actions
Use the tables below to inspect Fish Audio's 0 triggers, 0 search modules, and 3 actions.
Actions
3 action modules cover the full range of create, update, and delete operations.
- Create Speech to Text
- Create Text to Speech
- Make an API Call
Explore the fields available for each Fish Audio trigger, search, and action.
Actions
| Field | Type |
|---|---|
Audio FileRequired | text |
Language | text |
Ignore Timestamps | boolean |
| Field | Type |
|---|---|
Text | text |
Duration | number |
Segments | array |
| Field | Type |
|---|---|
TextRequired | text |
Model | choice |
Temperature | number |
Top P | number |
Reference ID | choice |
Prosody | object |
Prosody Speed | number |
Prosody Volume | number |
Chunk Length | number |
Normalize | boolean |
Format | choice |
Sample Rate | number |
MP3 Bitrate | choice |
Opus Bitrate | choice |
Latency | 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 |



