Zukijourney icon

Zukijourney

Zukijourney AI - Chat, Image Generation, Text-to-Speech, Image Upscaling, Translation
Join our community

Actions5

Overview

This node integrates with the Zukijourney AI platform to convert text into speech audio files. It allows users to input plain text and generate spoken audio in various voices using different AI speech models. This is useful for creating voiceovers, accessibility features, automated announcements, or any application requiring natural-sounding speech synthesis.

For example, you can input a product description or article text and generate an MP3 audio file narrated by a chosen AI voice, which can then be used in podcasts, videos, or interactive voice response systems.

Properties

Name Meaning
Model The AI model used for text-to-speech conversion. Options include: gpt-4o-mini-tts, tts-1, tts-1-hd.
Input Text The text string that will be converted into speech audio.
Voice The voice persona used for speech generation. Available options: Alloy, Echo, Fable, Onyx, Nova, Shimmer.

Output

The node outputs a JSON object along with binary audio data:

  • json: Contains metadata about the generated speech:

    • message: Confirmation message (e.g., "Speech generated successfully").
    • fileName: The filename of the generated audio file (e.g., speech_1680000000000.mp3).
    • model: The AI model used.
    • voice: The selected voice.
    • text: The original input text.

  • binary: Contains the generated speech audio file in MP3 format (audio/mpeg). This binary data can be used downstream in workflows for playback, storage, or further processing.

Dependencies

  • Requires an API key credential for authenticating requests to the Zukijourney AI service.
  • The node makes HTTPS POST requests to the Zukijourney API endpoint /v1/audio/speech.
  • No additional external dependencies beyond standard Node.js modules and n8n helpers.

Troubleshooting

  • Timeouts: The request to the API has a 30-second timeout. If your text is very long or network conditions are poor, you might encounter timeouts. Try reducing text length or checking network connectivity.
  • Authentication errors: Ensure the API key credential is correctly configured and valid.
  • Incomplete response error: If the returned audio data size does not match the expected content-length header, the node throws an error indicating an incomplete response. Retry the operation or check network stability.
  • Invalid input: Providing empty or invalid text may cause the API to fail. Always provide meaningful text input.
  • Voice or model unsupported: Using a voice or model name not supported by the API may result in errors. Use only the documented options.

Links and References

Discussion