Actions21
Overview
This custom n8n node named "Kim" supports a "绘图" (Drawing) operation, which appears to be related to generating images or visual content based on user prompts. The node also includes functionality related to text-to-speech voices, suggesting it can handle voice selection for audio output in other operations (not the drawing one).
Typical use cases include:
- Generating images from textual descriptions, e.g., "a cute cat eating a dinosaur".
- Selecting different voice profiles for speech synthesis in workflows that require audio output.
Practical examples:
- Creating AI-generated artwork by providing descriptive prompts.
- Using the node in multimedia automation where both image generation and voice narration are needed.
Properties
| Name | Meaning |
|---|---|
| 模型 (assistantId) | The model or intelligent agent used for processing. Can be any string; placeholder suggests free input. |
| 提示 (prompt) | The textual prompt describing what to draw, e.g., "a cute cat eating a dinosaur". Used only in the drawing operation. |
| 暂不支持 (notice) | A notice field indicating unsupported features for the drawing operation within certain resources. |
| 语音列表 (voice) | Selection of voice profiles for text-to-speech. Supports official voices (list mode) and cloned voices (string mode). Multiple tokens default to the first token. Required when using TTS features but hidden during drawing operation. |
Output
The node's execute() method delegates execution to an external router function (a.router.call(this)), so the exact output structure is not defined in this snippet. However, based on the context:
- For the 绘图 (drawing) operation, the output likely contains JSON data representing the generated image or metadata about the image generation result.
- The node supports voice selection for TTS, implying that in other operations it may output audio binary data or references to audio files.
- Binary data output (e.g., images or audio) would represent the generated media content.
Dependencies
- The node depends on an external routing module (
./actions/router) to handle the main execution logic. - It uses a version description module (
./actions/versionDescription) for metadata. - Voice list retrieval is implemented internally with a hardcoded list of voice options.
- No direct external API keys or credentials are referenced in the provided code, but the node likely requires appropriate API authentication configured in n8n to interact with underlying services for image generation or TTS.
Troubleshooting
- Since the core execution is routed externally, errors may arise from missing or misconfigured API credentials required by the backend services.
- Users might encounter issues if the prompt is empty or invalid for the drawing operation.
- The "暂不支持" notice indicates some features are not supported in certain resource-operation combinations; users should verify compatibility.
- If voice selection is required but no valid voice is chosen, the node may fail or produce unexpected results.
- Common error messages would relate to failed API calls, invalid parameters, or unsupported operations.
Links and References
- No direct external links are provided in the source code.
- For more information on voice options, see the internal voice list in the code.
- Refer to n8n documentation on creating custom nodes and handling external API integrations for further guidance.