What You Can Do
With the Typecast n8n node, you can:
- Automate content creation - Build fully automated YouTube or TikTok channels by combining RSS feeds, AI writing, and Typecast voices.
- Enhance customer experience - Send personalized voice messages via WhatsApp or email when a customer makes a purchase.
- Scale your reach - Automatically translate and dub your podcast or video content into multiple languages.
- Recommend voices - Search for voice candidates from a natural-language description.
- Stay notified - Get custom voice alerts on Slack or Discord for critical system updates or sales milestones.
Prerequisites
Before you start, make sure you have:
- n8n installed (n8n Cloud or self-hosted)
- Typecast API Key - Get yours here
Installation
Step 1: Install the Typecast Node
If you are using n8n Cloud, no separate installation is required. You can skip directly to the Quick Start section.
Quick Start: Your First Voice Generation
Let's create your first text-to-speech workflow!
Step 1: Add the Typecast Node
- Create a new workflow
- Click + to add a node
- Search for Typecast
- Select Typecast
- Choose an action from the list (e.g., Convert text to speech)
Step 2: Connect Your API Key (Credential)
After selecting the node, you need to configure your API key to connect with the Typecast API.
- In the node settings panel, click on the Credential to connect with field.
- Select - Create New Credential -.
- Enter your API key, which you can copy from the Typecast API console.
- Click Create to save your credentials.
Step 3: Configure Text to Speech
| Setting | What to Enter |
|---|---|
| Resource | Speech |
| Operation | Text to Speech |
| Voice ID | Select a voice from the dropdown (shows name, gender, age, and emotions) |
| Text | Your text to convert |
| Model | ssfm-v30 - recommended for best quality |
Selecting a Voice
The Voice ID field makes it easy to find the perfect voice:
- Click on the Voice ID dropdown
- Browse voices with their details (name, gender, age, available emotions)
- Use the search to filter by name or characteristics
- Select your preferred voice
Emotion Settings
Make your voice expressive with emotion controls!
For ssfm-v30
Two ways to add emotion:
AI automatically detects the best emotion from your text context. Perfect for natural conversations and storytelling.
Manually choose from 7 emotions: Normal, Happy, Sad, Angry, Whisper, Tone Up, Tone Down.
Smart Emotion Tip: Add "Previous Text" and "Next Text" to help the AI understand context better!
For ssfm-v21
Choose from 4 emotions: Normal, Happy, Sad, Angry
Adjust Emotion Intensity (0.0 - 2.0):
0.0- Completely neutral1.0- Standard (default)2.0- Maximum intensity
Additional Options
Customize your audio output:
| Option | Description | Default |
|---|---|---|
| Audio Format | WAV (high quality) or MP3 (smaller size) | WAV |
| Audio Pitch | Adjust pitch (-12 to +12 semitones) | 0 |
| Audio Tempo | Speed adjustment (0.5x to 2.0x) | 1.0 |
| Language | Override auto-detection if needed | Auto-detect |
| Seed | Unsigned integer (≥ 0). Use same seed for reproducible output | Random |
Step 4: Run and Listen
- Connect the nodes (Manual Trigger → Typecast)
- Click Execute Workflow
- Check the output - your audio file is ready!
- Click the audio to play it
Finding the Perfect Voice
Browse All Voices
- Add a Typecast node
- Set Resource →
Voice - Set Operation →
Get All Voices - Run the node to see all available voices
Recommend Voices
- Add a Typecast node
- Set Resource →
Voice - Set Operation →
Recommend Voices - Enter a text description and run the node
Recommendation results contain only voice_id, voice_name, and score. Use Get Voice or Get All Voices when your workflow needs metadata such as supported models, emotions, gender, age, or use cases before synthesis.
Filter Voices
Use filters to find exactly what you need:
| Filter | Options |
|---|---|
| Model | ssfm-v30 or ssfm-v21 |
| Gender | Male or Female |
| Age | Child, Teenager, Young Adult, Middle Age, Elder |
| Use Cases | Audiobook, Ads, E-learning, Game, Podcast, and more |
Troubleshooting
Node not appearing after installation
- Restart n8n completely
- Clear your browser cache
- Verify the installation in Settings → Community Nodes
Authentication failed
- Check your API key is correct
- Verify your key at Typecast API Console
- Make sure there are no extra spaces in the key
Voice ID not found
- Use the Get All Voices operation to find valid Voice IDs
- Voice IDs are case-sensitive (use lowercase
tc_...)
No audio generated
- Check that your text is not empty
- Verify you have sufficient API credits
- Check the error message in the node output