Venice AI

Use Venice AI for chat, image generation, embeddings, and more

Actions9

Overview

This node uses the Venice AI service to convert text into speech audio files. It is designed for scenarios where you want to generate spoken audio from textual content, such as creating voiceovers, accessibility features, automated announcements, or interactive voice responses. For example, you can input a paragraph of text and receive an MP3 audio file spoken in a selected voice at a specified speed.

Properties

Name Meaning
Text The text string that will be converted into speech.
Voice The voice ID to use for speech synthesis (e.g., "af_sky", "am_echo").
Format The audio output format. Options: MP3, Opus, AAC, FLAC, WAV, PCM.
Speed The speed multiplier for speech playback, ranging from 0.25 (slow) to 4 (fast).

Output

The node outputs a single item per input with the following structure:

  • json: An empty object {} since no JSON metadata is returned.
  • binary.data: Contains the generated audio file data in the chosen format (e.g., mp3, wav). This binary data can be used downstream for saving to disk, streaming, or further processing.

Dependencies

  • Requires an active connection to the Venice AI API service.
  • Needs an API authentication token configured in n8n credentials for Venice AI.
  • The node sends requests to the /audio/speech endpoint of the Venice AI API.

Troubleshooting

  • Missing or invalid API credentials: Ensure your Venice AI API key is correctly set up in n8n credentials.
  • No binary data property found: This error does not apply here since the node generates binary data internally.
  • Unsupported voice or format: Verify that the voice ID and audio format are valid and supported by Venice AI.
  • Speed out of range: The speed must be between 0.25 and 4; values outside this range may cause errors.
  • Network or API errors: Check network connectivity and API status if requests fail.

Links and References

Discussion