Venice Text to Speech icon

Venice Text to Speech

Convert text to speech with Venice.ai
Join our community

Overview

This node converts input text into speech audio using the Venice.ai text-to-speech API. It is useful for automating voice generation tasks such as creating audio narrations, voice prompts, or accessibility features. For example, you can input product descriptions or notifications and generate spoken audio files in various formats and voices.

Properties

Name Meaning
Text The text string to convert into speech audio.
Model The text-to-speech model to use. Currently only "tts-kokoro" is available.
Voice The voice persona for the generated speech. Options include various American and British male and female voices (e.g., Adam, Alice, Emma, Liam, Sky).
Format The audio format of the output file. Options: AAC, FLAC, MP3, Opus, PCM, WAV.
Options Additional settings:
• Speed: Playback speed from 0.25 to 4.0 (default 1).
• Streaming: Whether to stream audio sentence by sentence (true/false).

Output

The node outputs an array with one item per input. Each item contains:

  • json:
    • success: Boolean indicating if the request succeeded.
    • format: The audio format used (e.g., mp3).
    • contentType: The MIME type of the audio (e.g., audio/mpeg).
    • text: The original input text.
    • voice: The voice used for synthesis.
  • binary:
    • data: The generated audio file in binary form, named like venice_speech_<timestamp>.<format>.

This binary data can be used directly in workflows that handle audio files, such as saving to disk or sending via messaging platforms.

Dependencies

  • Requires an API key credential for the Venice.ai service.
  • The node makes authenticated HTTP POST requests to https://api.venice.ai/api/v1/audio/speech.
  • No additional environment variables are needed beyond the configured API authentication.

Troubleshooting

  • Common issues:
    • Invalid or missing API credentials will cause authentication errors.
    • Unsupported audio format or voice options may result in API errors.
    • Network connectivity problems can cause request failures.
  • Error messages:
    • Errors returned from the API will be thrown unless "Continue On Fail" is enabled, in which case error details appear in the output JSON.
  • Resolutions:
    • Verify the API key is correctly set up and has permissions.
    • Ensure selected voices and formats are valid options.
    • Check network access to the Venice.ai endpoint.

Links and References

Discussion