Neuphonic

Interact with the Neuphonic Text-to-Speech API

Text to Speech

AI-generated

Overview

This node integrates with the Neuphonic Text-to-Speech API to convert input text into spoken audio. It is useful in scenarios where automated voice generation is needed, such as creating audio versions of articles, generating voice prompts for IVR systems, or producing narration for videos and presentations. For example, a user can input a paragraph of text and receive an audio file in MP3 or WAV format that reads the text aloud.

Properties

Name Meaning
Text The text string that will be converted into speech.
Voice The voice style used for the speech output. Currently only "Default" is available.
Additional Fields Optional extra settings:
- Format The audio output format; options are "MP3" or "WAV".

Output

The node outputs JSON data containing the response from the Neuphonic API. This typically includes the generated audio content encoded or linked according to the requested format (MP3 or WAV). If binary data is returned, it represents the audio file corresponding to the synthesized speech.

Dependencies

  • Requires an API key credential for authenticating with the Neuphonic Text-to-Speech service.
  • The node sends POST requests to https://api.neuphonic.com/v1/tts with JSON payloads.
  • Proper configuration of the API key credential within n8n is necessary for successful operation.

Troubleshooting

  • Common issues:
    • Missing or invalid API key will cause authentication failures.
    • Providing empty or excessively long text may result in errors or truncated audio.
    • Unsupported audio formats or voices (beyond "default") are not accepted.
  • Error messages:
    • Authentication errors indicate problems with the API key setup.
    • Validation errors may occur if required fields like "Text" are empty.
  • Resolutions:
    • Ensure the API key credential is correctly configured and active.
    • Provide valid, non-empty text input.
    • Use supported audio formats ("mp3" or "wav") and the default voice option.

Links and References

Discussion