JSPM

n8n-nodes-groq-speech

1.1.2
  • ESM via JSPM
  • ES Module Entrypoint
  • Export Map
  • Keywords
  • License
  • Repository URL
  • TypeScript Types
  • README
  • Created
  • Published
  • Downloads 16
  • Score
    100M100P100Q50813F
  • License MIT

N8N Community Node for Groq Text-to-Speech API integration

Package Exports

    This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (n8n-nodes-groq-speech) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

    Readme

    n8n-nodes-groq-speech

    This is an N8N community node package for integration with Groq.com Text-to-Speech (TTS) API.

    Features

    • Text to audio conversion using Groq API
    • Support for multiple TTS models (playai-tts, playai-tts-arabic)
    • 19 different voices available
    • Speech speed control (0.25x to 4.0x)
    • Multiple output formats (MP3, WAV, FLAC, OGG)
    • Output as binary data for use in other nodes
    • NEW: Built-in Base64 encoding for direct API integration
    • NEW: WhatsApp-ready audio output format

    Installation

    To use this community node, you need to install it in your N8N environment:

    npm install n8n-nodes-groq-speech

    Configuration

    1. Get your Groq API key from: https://console.groq.com/keys
    2. IMPORTANT: Accept model terms at https://console.groq.com/playground?model=playai-tts (required before first use)
    3. Configure "Groq API" credentials in N8N with your API key
    4. Use the "Groq TTS" node in your workflows

    ⚠️ Important Setup Step

    Before using any TTS model, you must accept the terms of service for that specific model:

    Click on the model in the playground and accept the terms when prompted. This is a one-time requirement per model.

    Usage

    The node accepts the following parameters:

    • Text: The text to be converted to audio
    • Model: TTS model to use (playai-tts or playai-tts-arabic)
    • Voice: One of the 19 available voices
    • Response Format: Audio file format (MP3, WAV, FLAC, OGG)
    • Speed: Speech speed (0.25 to 4.0)
    • Output File Name: Custom name for the output file
    • Include Base64 Output: Generate base64 encoded audio for direct API usage

    Available Voices

    • Arista-PlayAI
    • Atlas-PlayAI
    • Basil-PlayAI
    • Briggs-PlayAI
    • Calum-PlayAI
    • Celeste-PlayAI
    • Cheyenne-PlayAI
    • Chip-PlayAI
    • Cillian-PlayAI
    • Deedee-PlayAI
    • Fritz-PlayAI
    • Gail-PlayAI
    • Indigo-PlayAI
    • Mamaw-PlayAI
    • Mason-PlayAI
    • Mikail-PlayAI
    • Mitch-PlayAI
    • Quinn-PlayAI
    • Thunder-PlayAI

    Output

    The node returns:

    • JSON: Metadata about the generated audio (success, filename, format, etc.)
    • Binary Data: The generated audio file, ready to be used by other nodes

    With Base64 Output Enabled:

    {
  "success": true,
  "fileName": "speech.mp3",
  "format": "mp3",
  "voice": "Fritz-PlayAI",
  "model": "playai-tts",
  "speed": 1.0,
  "textLength": 25,
  "binaryDataSize": 45678,
  "audioBase64": "UklGRnoGAABXQVZFZm10...",
  "audioDataUri": "data:audio/mp3;base64,UklGRnoGAAB...",
  "base64Enabled": true
}

## Use Cases

- Voice message generation for WhatsApp
- Audio creation for emails
- Voice announcement automation
- Audio content generation for social media
- Custom sound notification creation

### WhatsApp Integration Example

With the base64 output feature, you can send audio directly to WhatsApp APIs:

    [Trigger] → [Groq TTS] → [HTTP Request to WhatsApp API]

    
**Groq TTS Configuration:**
- Enable "Include Base64 Output" in Additional Fields
- Set desired voice and format

**HTTP Request Body:**
```json
{
  "number": "5511999999999",
  "mediatype": "audio", 
  "media": "{{$json.audioDataUri}}",
  "fileName": "{{$json.fileName}}"
}

    Available Output Fields:

    Standard Output:

    • success: Boolean indicating operation success
    • fileName: Generated audio file name
    • format: Audio format (mp3, wav, etc.)
    • voice: Selected voice name
    • model: TTS model used
    • speed: Speech speed applied
    • textLength: Length of input text
    • binaryDataSize: Size of generated audio in bytes

    With Base64 Output Enabled:

    • audioBase64: Raw base64 encoded audio data
    • audioDataUri: Complete data URI with MIME type
    • base64Enabled: Confirmation that base64 was generated

    Direct WhatsApp Integration

    No additional nodes needed! Simply:

    1. Enable "Include Base64 Output" in the Groq TTS node
    2. Use {{$json.audioDataUri}} directly in your WhatsApp API calls
    3. Send audio messages instantly

    Troubleshooting

    Common Issues

    1. "Model terms acceptance required": Visit the Groq playground and accept terms for your chosen model
    2. "Invalid API key": Verify your API key is correct and has TTS permissions
    3. "Rate limit exceeded": Wait a moment and try again, or check your Groq usage limits

    Error Messages

    The node provides detailed error messages to help diagnose issues:

    • Model terms errors include direct links to accept terms
    • API errors show the specific Groq error message
    • Network errors indicate connection problems

    Support

    For issues with this N8N node, please check:

    1. Your Groq API key is valid
    2. Model terms have been accepted
    3. Your text input is not empty
    4. The selected voice is compatible with your chosen model

    License

    MIT