Venice AI

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

Actions9

Audio → Text to Speech

AI-generated

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 select a specific voice and audio format to produce an audio file that can be played back in applications, websites, or devices.

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 output audio format. Options: MP3, Opus, AAC, FLAC, WAV, PCM.
Speed The speed of the speech playback, ranging from 0.25 (slow) to 4 (fast).

Output

The node outputs a single item per input with:

  • json: An empty JSON object {} since the main data is binary.
  • binary.data: Contains the generated audio file in the selected format. This binary data can be used downstream in workflows for saving to disk, uploading, or playing.

Dependencies

  • Requires an API key credential for the Venice AI service to authenticate requests.
  • The node makes HTTP POST requests to the Venice AI /audio/speech endpoint.
  • No additional environment variables are explicitly required beyond the API credential.

Troubleshooting

  • Missing Binary Data Property: If the input does not contain expected binary data when required (not applicable here but common in image operations), the node throws an error.
  • API Request Failures: Network issues or invalid credentials may cause request failures. Ensure the API key is valid and network connectivity is stable.
  • Invalid Parameter Values: Providing unsupported voice IDs or audio formats may result in errors from the API. Verify that the voice and format values are supported by Venice AI.
  • Speed Out of Range: The speed parameter must be between 0.25 and 4; values outside this range may cause errors or unexpected behavior.

Links and References

  • Venice AI Documentation (hypothetical link, replace with actual if available)
  • Audio format specifications:
    • MP3: MPEG Audio Layer III
    • Opus: Highly versatile audio codec
    • AAC: Advanced Audio Coding
    • FLAC: Free Lossless Audio Codec
    • WAV: Waveform Audio File Format
    • PCM: Pulse-code Modulation raw audio data

Discussion