Actions15
- Assistant Actions
- Assistant Event Actions
- Chat Actions
- Conversation Actions
- Voice Actions
Overview
The node provides an interface to convert text into speech using selectable voices. It is designed to interact with a voice synthesis API, allowing users to input text and receive audio output in the form of speech. This node is useful for automating voice generation tasks such as creating audio messages, voice notifications, or accessibility features.
Typical use cases include:
- Generating spoken versions of text content for podcasts or audiobooks.
- Creating voice alerts or announcements in automated workflows.
- Enhancing chatbots or virtual assistants with natural-sounding speech output.
Properties
| Name | Meaning |
|---|---|
| Voice | Select the voice to use for the conversion. Options include a list of available voices or specifying a voice by ID. |
| Include ElevenLabs Voices | Boolean option to include additional voices from the ElevenLabs provider in the voice selection. |
| ElevenLabs API Key Reference | Required when including ElevenLabs voices; a reference to the API key stored securely in integration secrets. |
| Text | The text string that will be converted into speech. |
Output
The node outputs JSON data containing the result of the text-to-speech conversion. Typically, this includes metadata about the generated audio and possibly a URL or binary data representing the synthesized speech audio file.
If the node supports binary data output, it would represent the actual audio content (e.g., MP3 or WAV) corresponding to the spoken text.
Dependencies
- Requires an API key credential for authenticating requests to the Telnyx AI service.
- If ElevenLabs voices are included, an additional API key reference for ElevenLabs must be provided via integration secrets.
- Network access to the Telnyx AI API endpoint (
https://api.telnyx.com) is necessary.
Troubleshooting
- Missing or invalid API keys: Ensure that the required API keys are correctly configured and referenced in the node settings.
- Voice not found or unsupported: Verify that the selected voice exists and is supported by the service, especially when toggling the inclusion of ElevenLabs voices.
- Text input errors: Confirm that the text property is not empty and contains valid characters for speech synthesis.
- Network issues: Check connectivity to the Telnyx API endpoint and ensure no firewall or proxy is blocking requests.
Links and References
- Telnyx AI Documentation
- ElevenLabs Voice Synthesis
- General n8n documentation on creating custom nodes