Actions7
- Voice Actions
- Speech Actions
Overview
The node integrates with the ElevenLabs API to convert text into speech audio. It allows users to input text and select a voice, then generates an audio file in various formats based on the selected options. This is useful for automating voiceover creation, generating audio content for accessibility, or creating dynamic spoken responses in applications.
Practical examples:
- Creating narrated videos by converting script text to speech.
- Generating audio versions of articles or blog posts.
- Building interactive voice assistants that respond with natural-sounding speech.
Properties
| Name | Meaning |
|---|---|
| Voice | Select the voice to use for the conversion. Can be chosen from a searchable list or specified by ID. |
| Text | The text string that will be converted into speech audio. |
| Additional Options | A collection of optional settings to customize the speech output: |
| - Model | Select the speech synthesis model to use, either from a list or by specifying an ID. |
| - Output Format | Choose the audio format and quality of the generated speech. Options include MP3, PCM, ULAW, ALAW, OPUS with various bitrates and sample rates. |
| - Language Code | ISO 639-1 language code to enforce a specific language for the speech model (e.g., "en" for English). |
| - Voice Settings | JSON object to override stored voice parameters such as stability, similarity boost, style, speaker boost usage, and speed. |
Output
The node outputs JSON data containing the generated speech audio. The audio is provided in the selected output format and can be used directly or saved as a binary file in subsequent workflow steps. The binary data represents the synthesized speech corresponding to the input text.
Dependencies
- Requires an API key credential for ElevenLabs API authentication.
- Needs network access to
https://api.elevenlabs.io/v1. - No additional environment variables are explicitly required beyond the API key configuration.
Troubleshooting
Common issues:
- Invalid or missing API key will cause authentication errors.
- Selecting a voice or model ID that does not exist may result in "not found" errors.
- Providing unsupported output formats or malformed JSON in voice settings can cause request failures.
- Network connectivity problems will prevent API calls.
Error messages and resolutions:
- 401 Unauthorized: Check that the API key credential is correctly configured and valid.
- 404 Not Found: Verify that the voice and model IDs exist and are accessible.
- 400 Bad Request: Ensure all required fields are filled and JSON inputs (like voice settings) are properly formatted.
- Timeouts or network errors: Confirm internet connectivity and API endpoint availability.