> ## Documentation Index
> Fetch the complete documentation index at: https://typecast.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Zapier

<Info>
  [Zapier](https://zapier.com/) is the most popular workflow automation platform. With the Typecast integration, you can convert text to speech automatically - no coding required!
</Info>

## What You Can Do

With the Typecast Zapier integration, you can:

- **Generate voiceovers** from any text automatically
- **Choose from 600\+ 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)
- **Recommend voices** from a text description, then fetch voice details before synthesis when needed
- **Connect to other apps** - send audio via email, save to cloud storage, post to Slack, etc.

---

## Prerequisites

Before you start, make sure you have:

1. **Zapier account** - [Sign up here](https://zapier.com/sign-up) if you don't have one
2. **Typecast API Key** - [Get yours here](https://studio.typecast.ai/developers/api/)

---

## Installation

### Step 1: Connect Your Typecast Account

When you first use Typecast in a Zap:

1. You'll be prompted to connect your Typecast account
2. Enter your **Typecast API Key**
3. Click **Yes, Continue**

<Tip>
  You can get your API key from the [Typecast API Console](https://studio.typecast.ai/developers/api/).
</Tip>

---

## Quick Start: Your First Voice Generation

Let's create a simple Zap that generates speech every hour!

### Step 1: Create a New Zap

1. Go to [Zapier Dashboard](https://zapier.com/app/assets/zaps)
2. Click **\+ Create** → **New Zap**

<Frame caption="Zapier Zaps dashboard">
  ![Zapier Zaps dashboard showing the Create button](/images/zapier-zaps-dashboard.webp)
</Frame>

### Step 2: Set Up the Trigger

For this example, we'll use a Schedule trigger:

1. Click on the **Trigger** step
2. Search for **Schedule** and select it
3. Choose **Every Hour** as the event
4. Click **Continue** and **Test trigger**

<Frame>
  ![Image](/images/image-7.webp)
</Frame>

### Step 3: Add Typecast Action

1. Click on the **Action** step
2. Search for **Typecast**
3. Select **Typecast**

<Frame>
  ![Image](/images/image-8.webp)
</Frame>

4. Choose **Create Speech From Text** as the event

<Frame>
  ![Image](/images/image-9.webp)
</Frame>

### Step 4: Configure Text to Speech

<Frame>
  ![Image](/images/image-10.webp)
</Frame>

| Setting | What to Enter |
| --- | --- |
| **Text** | Your text to convert (required) |
| **Model** | `ssfm-v30 (Recommended)` - latest model with best quality |
| **Voice** | Select from the dropdown (required) |
| **Language** | Auto-detected, or select manually |
| **Emotion Type** | `Preset` or `Smart` (v30 only) |
| **Emotion Preset** | Normal, Happy, Sad, Angry, Whisper, etc. |

### Step 5: Test and Publish

1. Click **Continue** to go to the Test step
2. Click **Test step** to generate sample audio
3. If successful, click **Publish** to activate your Zap

<Note>
  The generated audio URL will be available as output data. You can use it in subsequent steps to send via email, upload to cloud storage, or post to Slack.
</Note>

---

## Available Actions

### Create Speech From Text

Converts text to speech using Typecast AI voice models.

**Inputs:**

| Field | Required | Description |
| --- | --- | --- |
| Text | Yes | Text to convert (max 2000 characters) |
| Model | Yes | `ssfm-v30` (recommended) or `ssfm-v21` |
| Voice | Yes | Select from 600\+ available voices |
| Language | No | ISO 639-3 code (auto-detected if not set) |
| Emotion Type | No | `Preset` or `Smart` (context-aware, 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) |
| Volume | No | 0 to 200 (default: 100) |
| Audio Pitch | No | -12 to \+12 semitones (default: 0) |
| Audio Tempo | No | 0.5x to 2.0x speed (default: 1.0) |
| Audio Format | No | WAV or MP3 |

**Outputs:**

- Audio File URL
- Speech ID
- Duration (seconds)
- Content Type

### List Voices (Search)

Lists all available voice models with enhanced metadata.

**Filters:**

- Model (ssfm-v30, ssfm-v21)
- Gender (Male, Female)
- Age (Child, Teenager, Young Adult, Middle Age, Elder)
- Use Cases (Audiobook, Podcast, E-learning, etc.)

### Get Voice by ID (Search)

Get detailed information for a specific voice including supported emotions per model.

### Recommend Voices (Search)

Find voice candidates from a text description.

**Inputs:**

| Field | Required | Description |
| --- | --- | --- |
| Query | Yes | Text describing the desired style, mood, language, use case, or content context |
| Count | No | Number of recommendations to return (1-10, default: 5) |

**Outputs:**

- Voice ID
- Voice Name
- Score

The recommendation response contains only `voice_id`, `voice_name`, and `score`; use List Voices or Get Voice by ID when a Zap needs detailed metadata before synthesis.

---

## Emotion Settings

Make your voice expressive with emotion controls!

### For SSFM-V30 (Latest Model)

Two ways to add emotion:

<CardGroup cols={2}>
  <Card title="Smart Emotion" icon="wand-magic-sparkles">
    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.
  </Card>

  <Card title="Preset Emotion" icon="sliders">
    Manually choose from 7 emotions: Normal, Happy, Sad, Angry, Whisper, Tone Up, Tone Down.
  </Card>
</CardGroup>

### 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

---

## Example Use Cases

<AccordionGroup>
  <Accordion title="Daily News Podcast">
    1. **Trigger**: RSS feed with new articles
    2. **Action**: Typecast creates audio from article summary
    3. **Action**: Upload to podcast hosting platform
  </Accordion>

  <Accordion title="Customer Support Auto-Reply">
    1. **Trigger**: New support ticket
    2. **Action**: AI generates response text
    3. **Action**: Typecast converts to voice message
    4. **Action**: Send via email or SMS
  </Accordion>

  <Accordion title="E-learning Content">
    1. **Trigger**: New lesson content in Google Sheets
    2. **Action**: Typecast generates narration
    3. **Action**: Upload to Google Drive
    4. **Action**: Notify team via Slack
  </Accordion>
</AccordionGroup>

---

## Troubleshooting

<AccordionGroup>
  <Accordion title="Can't find Typecast in Zapier">
    Search for "Typecast" in the Zapier app directory. Make sure you're using the latest available version.
  </Accordion>

  <Accordion title="Authentication failed">
    - Check your API key is correct
    - Verify your key at [Typecast API Console](https://studio.typecast.ai/developers/api/)
    - Make sure there are no extra spaces in the key
  </Accordion>

  <Accordion title="Voice dropdown is empty">
    - Check your API key has proper permissions
    - Try refreshing the field by clicking the refresh icon
  </Accordion>

  <Accordion title="No audio generated">
    - Check that your text is not empty
    - Verify you have sufficient API credits
    - Check the error message in the test output
  </Accordion>
</AccordionGroup>

---

## Resources

<CardGroup cols={2}>
  <Card title="Voice Library" icon="microphone" href="https://studio.typecast.ai/developers/api/voices">
    Browse all available voices
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference">
    Explore the Typecast API
  </Card>

  <Card title="Zapier Help" icon="circle-question" href="https://help.zapier.com/">
    Zapier documentation and support
  </Card>
</CardGroup>

## Control silence duration

In Typecast **2.2.7 or later**, set **Remaining Silence (ms)** in standard, streaming, or timestamp speech actions. The input key is `remove_silence_ms`; leave it blank to disable processing.

`remove_silence_ms` specifies the **silence duration to retain**, not the amount to remove. Use an integer from `0` to `1000` ms. `0` removes detected silence; omission or `null` disables duration-based silence removal.

Standard, streaming, and timestamp TTS use `output.remove_silence_ms`; Compose uses `segments[].output.remove_silence_ms` on each `tts` segment. Returned timestamps align with the processed audio, and explicit `pause` segments are preserved.

Streaming's default leading-silence trimming is separate. Small values such as `0` can leave gaps between playable chunks; allow sufficient playback buffering and test with your content.