n8n-nodes-soniox-api
v0.5.5
Published
n8n node for Soniox Speech-to-Text API
Maintainers
Readme
n8n-nodes-soniox-api
WIP VERSION! NOT FOR PRODUCTION USE! Has not working yet!
This is an n8n community node that integrates Soniox Speech-to-Text API — a high-accuracy, multilingual speech recognition system.
Features:
- 🎯 One-node transcription (like Whisper node)
- 🌍 60+ languages supported
- 🎭 Speaker diarization
- 🔄 Real-time translations
- ⚡ Async processing with auto-polling
n8n is a fair-code licensed workflow automation platform.
Installation · Operations · Credentials · Usage · Resources
Installation
n8n Community Nodes
- Go to Settings → Community Nodes in your n8n instance
- Click Install and enter:
n8n-nodes-soniox-api - Click Install
- Restart n8n to load the node
Manual Installation
To get started locally, install the node in your n8n root directory:
cd ~/.n8n
npm install n8n-nodes-soniox-apiFor Docker-based n8n installations, add the package to your n8n installation:
docker exec -it n8n npm install n8n-nodes-soniox-apiDevelopment
For local development and testing:
git clone https://github.com/mazixs/n8n-nodes-soniox-api.git
cd n8n-nodes-soniox-api
npm install
npm run build
npm link
# Link to your n8n installation
cd ~/.n8n
npm link n8n-nodes-soniox-apiOperations
Transcription Operations (Recommended)
- Transcribe 🆕 — All-in-one audio transcription (like Whisper node)
- Input: Binary audio data
- Output: Complete transcript with text + tokens + metadata
- Automatically handles: upload → create → wait → get transcript
- Configurable: model, language, speaker diarization, translations, timeout
- Get — Retrieve existing transcription result by ID
- List — List all transcriptions (with pagination)
File Operations (Advanced)
- Upload — Upload audio files (multipart/form-data support)
- Get — Retrieve file by ID
- Get All — List all files (with pagination)
- Delete — Delete a file
Model Operations
- Get All — List available speech recognition models
Deprecated Operations
The following operations still work but will be removed in v0.6.0:
- Create → use Transcribe instead
- Create and Wait → use Transcribe instead
- Get By File → use Get instead
Credentials
Setting up Credentials
- In n8n, navigate to Credentials → Add Credential → Soniox API
- Enter your credentials:
- API Key: Get your API key from console.soniox.com
- API URL:
https://api.soniox.com/v1(default)
- Click Save
Usage
Quick Start (Recommended)
The simplest way to transcribe audio - just one node:
[Read Binary File] → [Soniox: Transcribe] → Done!Node Configuration:
Soniox: Transcribe
- Resource:
Transcription - Operation:
Transcribe - Binary Property:
data - Model:
Realtime or Async(or any model from dropdown) - Additional Fields:
- Language:
en(optional, auto-detected if not specified) - Context: Domain-specific terms (optional)
- Translation Languages:
ru,es,fr(optional) - Enable Speaker Diarization:
true(optional)
- Language:
Output:
{
"transcript": {
"text": "Full transcribed text here",
"tokens": [
{"text": "Hello", "start_ms": 10, "confidence": 0.95}
]
},
"status": "completed",
"model": "stt-async-v3",
"audio_duration_ms": 16079
}Advanced Workflow (Multiple Nodes)
For more control, use separate nodes:
[Read Binary File]
↓
[Soniox: File Upload]
↓
[Soniox: Create and Wait]
↓
[Process Result]Note: The advanced workflow requires 2-3 nodes. We recommend using Transcribe for simplicity.
Features
- ✅ Retry Logic — Automatic retry with exponential backoff for failed requests
- ✅ Rate Limiting — Smart handling of 429 responses with Retry-After headers
- ✅ Timeout Control — Configurable timeouts for API and file upload operations
- ✅ Type Safety — Full TypeScript implementation with n8n-workflow types
- ✅ Error Handling — Comprehensive error messages for debugging
Resources
Development
Build
npm install
npm run buildLint
npm run lint
npm run lintfix # Auto-fix issuesTesting
Link the node to your n8n installation:
npm run build && npm link
cd ~/.n8n && npm link n8n-nodes-soniox-api
n8n startThen test the node in your n8n workflows.
Version History
See CHANGELOG.md for detailed release notes.
License
Contributing
Contributions are welcome! Please read CONTRIBUTING.md for details on our code of conduct and the process for submitting pull requests.
Author
mazix
- GitHub: @mazixs
- npm: n8n-nodes-soniox-api
Support
If you encounter issues or have questions:
- Check the documentation
- Search existing issues
- Create a new issue if needed
Made with ❤️ for the n8n community
