translation-vocantai

Audio file transcription services. Your speech. Private.

Package Information

Downloads: 1 weekly / 4 monthly
Latest Version: 1.0.3
Author: VocantAI

Available Nodes

Vocant AI icon
Vocant AI
Upload and process audio file with Vocant AI
Vocant AI Callback icon
Vocant AI Callback
Receives transcription results from Vocant AI
VocantAI Speech-to-Text icon
VocantAI Speech-to-Text
Upload and download transcription in one node

Documentation

Banner image

@vocantai/n8n-nodes-translation-vocantai

This is an n8n community node package that provides audio transcription services using VocantAI. It lets you upload audio files and receive transcribed text in your n8n workflows.

VocantAI offers private, secure speech-to-text transcription services with high accuracy and fast processing times.

n8n is a fair-code licensed workflow automation platform.

Installation
Operations
Compatibility
Usage
Resources
Version history

Installation

Follow the installation guide in the n8n community nodes documentation.

For manual installation:

npm install @vocantai/n8n-nodes-translation-vocantai

Operations

VocantAI Node

  • Upload Audio: Upload audio files for transcription using presigned URLs
  • Get Transcription: Retrieve completed transcription results
  • Check Status: Monitor transcription job status

VocantAI Callback Trigger

  • Webhook Trigger: Receives transcription completion callbacks
  • File Download: Automatically downloads completed transcription files
  • Binary Output: Provides transcribed text as binary data for further processing

Compatibility

  • Minimum n8n version: 1.0.0
  • Tested against n8n versions: 1.0.0 - 1.5.0
  • Node.js version: 20+

Usage

Setting up Credentials

  1. Create a VocantAI account and obtain your API key
  2. In n8n, add new credentials for "Vocant AI API"
  3. Enter your API key

Basic Workflow

  1. File Input: Use nodes like Google Drive, HTTP Request, or Read Binary File to provide audio files
  2. VocantAI Upload: Add the VocantAI node to upload your audio file
  3. Callback Setup: Add the VocantAI Callback trigger to receive results
  4. Process Results: Use the transcribed text in subsequent workflow steps

Example Workflow

Google Drive → VocantAI → [Process continues...]
                ↓
VocantAI Callback → Write Binary File / Further Processing

Configuration Options

  • Binary Input Field: Specify which field contains the audio file (default: "data")
  • Callback URL: Your n8n webhook URL for receiving results
  • Use Original Filename: Toggle to use original filename as base for transcription file

Supported Audio Formats

VocantAI supports various audio formats including:

  • MP3
  • WAV
  • M4A
  • FLAC
  • And more...

Resources

Version history

1.0.3

  • New: Added VocantAI Speech-to-Text node for single-step audio transcription (upload, poll, download) — a direct replacement for OpenAI Translate.
  • Improvement: Simplified workflow for translation tasks.
  • All previous versions are deprecated.

Deprecated Versions

  • 1.0.2 (deprecated)
  • 1.0.1 (deprecated)
  • 1.0.0 (deprecated)
  • 0.1.10 (deprecated)
  • 0.1.9 (deprecated)
  • 0.1.8 (deprecated)
  • 0.1.7 (deprecated)
  • 0.1.6 (deprecated)
  • 0.1.5 (deprecated)
  • 0.1.4 (deprecated)
  • 0.1.3 (deprecated)
  • 0.1.2 (deprecated)
  • 0.1.1 (deprecated)
  • 0.1.0 (deprecated)

Development

To set up the development environment:

git clone https://github.com/VocantAI/n8n-nodes-translation-vocantai.git
cd n8n-nodes-translation-vocantai
pnpm install
pnpm run build

License

MIT

Support

For issues and feature requests, please visit our GitHub Issues page.

For VocantAI API support, contact: dev@vocant.ai

Discussion