Actions21
Overview
This node provides functionality for document and image parsing, with additional support for text-to-speech (TTS) voice selection. It is designed to process input data such as documents or images and convert them into a parsed format, potentially including audio output using selectable voice models. This node is useful in scenarios where automated extraction of information from documents or images is needed, combined with the ability to generate spoken versions of the content.
Practical examples include:
- Extracting text from scanned documents or images and converting it into structured data.
- Generating audio narration of parsed text using different voice personas.
- Automating workflows that require both visual content analysis and speech synthesis.
Properties
| Name | Meaning |
|---|---|
| 模型 (assistantId) | The model or intelligent agent used for processing. Can be any string; placeholder suggests it can be arbitrary if unknown. |
| 语音列表 (voice) | Selection of TTS voices. Supports multiple modes: - Official voices (a predefined list of named voices) - Cloned voices (custom voice strings). Multiple tokens default to using the first token. |
The "语音列表" property is required when using TTS features and offers a searchable list of official voice options or allows specifying custom cloned voices.
Output
The node outputs JSON data representing the parsed results of the input documents or images. The exact structure depends on the implementation of the routing logic but generally includes extracted textual or structured data.
If TTS is enabled, the node may also output audio data corresponding to the selected voice, though binary output details are not explicitly shown in the source.
Dependencies
- The node relies on an internal router module (
./actions/router) to handle execution logic. - It uses a version description module (
./actions/versionDescription) for metadata. - For voice selection, it supports a dynamic search method to retrieve available TTS voices.
- Requires configuration of API keys or authentication tokens to access TTS services or document/image parsing backends (not detailed in the code).
Troubleshooting
- Voice selection issues: If no voices appear or TTS fails, ensure the voice list search method is correctly configured and that valid tokens or credentials are provided.
- Parsing errors: Failures in document or image parsing might result from unsupported file formats or corrupted inputs.
- Empty or invalid output: Verify that the input data is correctly passed to the node and that the chosen model or assistant ID is valid.
- API or service errors: Network issues or invalid credentials can cause execution failures; check connectivity and authentication settings.
Links and References
- No direct external links are provided in the source code.
- For more information on TTS voices and usage, consult the documentation of the underlying TTS service integrated with this node.
- Refer to n8n community forums or official docs for guidance on configuring API credentials and troubleshooting common node issues.