Actions9
- Chat Actions
- Image Actions
- Audio Actions
- Embedding Actions
- Model Actions
Overview
The node provides a Text to Speech (TTS) capability using the Venice AI service. It converts input text into spoken audio in various formats and voices, allowing users to generate speech audio files from textual content. This is useful for creating voiceovers, accessibility features, automated announcements, or any application requiring synthetic speech output.
For example, you can input a paragraph of text and select a preferred voice and audio format to produce an MP3 file that reads the text aloud. Adjusting the speech speed allows customization of how fast or slow the speech sounds.
Properties
| Name | Meaning |
|---|---|
| Text | The text string to convert 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 of the speech playback, ranging from 0.25 (slowest) to 4 (fastest). |
Output
The node outputs binary audio data representing the synthesized speech. The binary data is stored under a property named data with a filename extension matching the selected audio format (e.g., audio.mp3). The JSON output is empty ({}), as the main result is the binary audio content.
Dependencies
- Requires an API key credential for the Venice AI service.
- The node makes HTTP POST requests to the Venice AI
/audio/speechendpoint. - No additional environment variables are explicitly required beyond the API authentication.
Troubleshooting
- Missing or invalid API credentials: Ensure the API key credential is correctly configured in n8n.
- Invalid voice ID: Use a valid voice identifier supported by the Venice AI TTS model.
- Unsupported audio format: Choose one of the supported formats listed in the properties.
- Speed out of range: Provide a speed value between 0.25 and 4; values outside this range may cause errors.
- Empty text input: The "Text" property is required; providing empty text will likely cause the request to fail.
- Network or API errors: Check network connectivity and Venice AI service status if requests fail.
Links and References
- Venice AI official documentation (for API details and voice options)
- n8n documentation on working with binary data and custom nodes