Make

Make is a powerful visual workflow automation platform. With the Typecast integration, you can convert text to speech automatically — no coding required!

What You Can Do

With the Typecast Make integration, you can:

Generate voiceovers from any text automatically
Choose from 500+ voices with different genders, ages, and styles
Apply emotions (happy, sad, angry, whisper, and more)
Use Smart Emotion for context-aware voice synthesis (ssfm-v30)
Filter voices by gender, age group, and use case
Connect to 1500+ apps — send audio via email, save to cloud storage, post to Slack, etc.

Prerequisites

Before you start, make sure you have:

Make account — Sign up here if you don’t have one
Typecast API Key — Get yours here
Invite link access — Accept the invite

Installation

Step 1: Accept the Invite

Since Typecast is currently in private beta, you need to accept the invite first:

Click the invite link
Log in to your Make account (or create one)
Click Install to add Typecast to your apps

Step 2: Connect Your Typecast Account

When you first use Typecast in a scenario:

Click Create a connection
Enter a name for your connection (e.g., “My Typecast”)
Enter your Typecast API Key
Click Save

You can get your API key from the Typecast API Console.

Quick Start: Your First Voice Generation

Let’s create a simple scenario that generates speech!

Step 1: Create a New Scenario

Go to Make Dashboard
Click + Create a new scenario

Step 2: Add Typecast Module

Click the + button to add a module
Search for Typecast
Select Typecast from the results

Step 3: Select Action

Choose Generate a Speech from the available actions.

Typecast action options - Generate a Speech, Get Voices

Step 4: Configure Text to Speech

Setting	What to Enter
Text	Your text to convert (required)
Voice ID	Enter a voice ID (e.g., `tc_60e5426de8b95f1d3000d7b5`)
Model	`ssfm-v30` — latest model with best quality
Language	Auto-detected, or select manually
Emotion Type	`Preset` or `Smart` (ssfm-v30 only)

Use the Get Voices module first to find available Voice IDs. You can filter by gender, age, and use case!

Step 5: Test and Activate

Click OK to save the module configuration
Click Run once to test your scenario
If successful, toggle the scenario to ON to activate it

The generated audio will be returned as binary data (WAV or MP3). You can use it in subsequent modules to send via email, upload to cloud storage, or process further.

Available Modules

Generate a Speech (Action)

Converts text to speech using Typecast AI voice models. Inputs:

Field	Required	Description
Text	Yes	Text to convert (max 2000 characters)
Voice ID	Yes	Voice identifier (format: `tc_xxxxx`)
Model	Yes	`ssfm-v30` (recommended) or `ssfm-v21`
Language	No	ISO 639-3 code (auto-detected if not set)
Emotion Type	No	`Preset` or `Smart` (context-aware, ssfm-v30 only)
Emotion Preset	No	Normal, Happy, Sad, Angry, Whisper, Tone Up, Tone Down
Emotion Intensity	No	0.0 to 2.0 (default: 1.0)
Target LUFS	No	-70 to 0 (e.g. -14 for streaming, -23 for broadcast)
Pitch	No	-12 to +12 semitones (default: 0)
Tempo	No	0.5x to 2.0x speed (default: 1.0)
Audio Format	No	WAV or MP3
Seed	No	For reproducible results

Outputs:

Audio file (binary data)
File name

Get Voices (Search)

Lists all available voice models with filtering options. Filters:

Field	Description
Model	Filter by `ssfm-v30` or `ssfm-v21`
Gender	Male or Female
Age	Child, Teenager, Young Adult, Middle Age, Elder
Use Cases	Audiobook, Podcast, E-learning, Ads, Game, etc.
Limit	Maximum number of results

Output (per voice):

Voice ID
Voice Name
Supported Models and Emotions
Gender and Age Group
Recommended Use Cases

Finding the Right Voice

To find the perfect voice for your project:

Add Get Voices Module

Add the Get Voices module to your scenario

Apply Filters

Filter by gender, age group, and use case to narrow down options

Copy Voice ID

From the results, copy the voice_id you want to use

Use in Generate a Speech

Paste the Voice ID into the Generate a Speech module

Emotion Settings

Make your voice expressive with emotion controls!

For ssfm-v30 (Latest Model)

Two ways to add emotion:

Smart Emotion

AI automatically detects the best emotion from your text context. Perfect for natural conversations and storytelling.Add “Previous Text” and “Next Text” for better context understanding.

Preset Emotion

Manually choose from 7 emotions: Normal, Happy, Sad, Angry, Whisper, Tone Up, Tone Down.

When you select an Emotion Type, additional fields appear dynamically:

Preset: Shows “Emotion Preset” dropdown and “Emotion Intensity” slider
Smart: Shows “Previous Text” and “Next Text” context fields

Smart emotion settings with context in Make

For ssfm-v21

Choose from 4 emotions: Normal, Happy, Sad, Angry Adjust Emotion Intensity (0.0 - 2.0):

0.0 — Completely neutral
1.0 — Standard (default)
2.0 — Maximum intensity

Model Comparison

Feature	ssfm-v21	ssfm-v30
Emotions	4 types	7 types
Languages	27	37
Smart Mode	No	Yes
Quality	Stable	Enhanced
Recommendation	Production	Latest Features

Example Use Cases

Automated Video Narration

Trigger: New row added in Google Sheets
Action: Typecast generates voiceover from script text
Action: Upload audio to Google Drive
Action: Notify team via Slack

Multilingual Content Creation

Trigger: New content in CMS
Action: Translate text with DeepL or Google Translate
Action: Typecast creates audio in each language
Action: Save to cloud storage organized by language

E-learning Course Production

Trigger: New lesson module approved
Action: Typecast generates professional narration
Action: Upload to LMS (Teachable, Thinkific, etc.)
Action: Update course status in Airtable

Podcast Episode Intros

Trigger: Scheduled daily at 6 AM
Action: Fetch latest news headlines
Action: Typecast creates intro with energetic voice
Action: Append to podcast audio file

Advanced: Working with Audio Output

The Generate a Speech module outputs audio as binary data. Here’s how to use it:

Save to Cloud Storage

Connect a Google Drive, Dropbox, or OneDrive module after Typecast:

Map the audio data to the file content
Set filename with .wav or .mp3 extension based on your Audio Format setting

Send via Email

Use Gmail or SMTP module:

Add the audio as an attachment
Map the file data and set the correct MIME type (audio/wav or audio/mpeg)

Process Further

Use HTTP module to:

Upload to a custom server
Send to a video editing API
Store in your own database

Troubleshooting

Can't find Typecast in Make

Make sure you’ve accepted the invite link first. Typecast is currently in private beta.

Connection failed

Check your API key is correct
Verify your key at Typecast API Console
Make sure there are no extra spaces in the key

Invalid Voice ID error

Voice IDs must start with tc_ prefix
Use the Get Voices module to find valid Voice IDs
Make sure the voice supports your selected model

No audio generated

Check that your text is not empty
Verify you have sufficient API credits
Check if the text exceeds 2000 characters

Smart Emotion not working

Smart Emotion is only available with ssfm-v30 model
Make sure you’ve selected “Smart” as the Emotion Type
Provide context in Previous Text and/or Next Text fields

Audio quality issues

Try switching between WAV and MP3 formats
Adjust Target LUFS, Pitch, and Tempo settings
Use a different voice that better suits your content

Supported Languages

Typecast supports 37 languages with the ssfm-v30 model:

Popular
European
Asian

English, Korean, Japanese, Chinese, Spanish, French, German, Portuguese

Resources

Get Invite Access

Accept the invite to use Typecast

Voice Library

Browse all available voices

API Reference

Explore the Typecast API

Make Help Center

Make documentation and support

GET STARTED

SDKs

INTEGRATIONS

What You Can Do

Prerequisites