Agent.ai Documentation home page
Search...
⌘K
Ask AI
Support
Platform
Platform
Search...
Navigation
Generate Audio Output
Guides
API Reference
Recipes
Documentation
Community
Using Agent.ai
Welcome
AI Agents Explained
Security & Privacy
Marketplace Credits
Rate Limits
Profile
Settings
Integrations
Agent Team
Agent Runs
Agent Requests
For Builders
Builder Overview
Public Agent Policy
LLM Models
Action Availability
Knowledge Base
Secrets
Serverless Functions
Snippets
Clone an Agent
MCP Server
Lists in For Loops
Output Formatting
Actions
Get User Input
Get User File
Get User List
Get User KBs and Files
Click Go to Continue
Wait for User Confirmation
Get Bluesky Posts
Enrich with Breeze Intelligence
Get Data from Builder's Knowledge Base
Get Data from User's Uploaded Files
Get Instagram Followers
Get Instagram Profile
Get LinkedIn Activity
Get LinkedIn Profile
Get Twitter Users
Get Recent Tweets
Google News Data
Search Bluesky Posts
Search Results
Web Page Content
Web Page Screenshot
YouTube Channel Data
YouTube Search Results
Get HubSpot CRM Object
Add HubSpot CRM Object
Update HubSpot CRM Object
Get HubSpot Owners
Get HubSpot Object Properties
Get Assigned Company
Use GenAI (LLM)
Generate Image
Set Variable
Add to List
Continue or Exit Workflow
If/Else Statement
For Loop
End If/Else/For Statement
Show User Output
Send Message
Create Blog Post
Save To Google Doc
Format Text
Post to Bluesky
Save To File
Convert File
Call Serverless Function
Invoke Web API
Invoke Other Agent
Store Variable to Database
Get Variable from Database
On this page
Overview
Use Cases
Configuration Fields
Text to Speech
Output Variable Name
Generate Audio Output
Overview
Convert text into speech using AI-powered text-to-speech models, creating natural-sounding audio outputs.
Use Cases
Accessibility
: Create audio versions of written content.
Marketing
: Generate voiceovers for advertisements or presentations.
Interactive Applications
: Provide audio feedback or instructions in workflows.
Configuration Fields
Text to Speech
Description
: Enter the text to be converted into speech.
Example
: “Welcome to our service!” or “Your order has been confirmed.”
Required
: Yes
Output Variable Name
Description
: Assign a variable name to store the generated audio.
Example
: “audio_output” or “speech_clip.”
Validation
: Only letters, numbers, and underscores (_) are allowed.
Required
: Yes
Assistant
Responses are generated using AI and may contain mistakes.