douyinTranscript icon

douyinTranscript

抖音视频下载、解析和转录工具

Actions2

Overview

This node is designed to work with Douyin (TikTok China) videos, providing tools to download, parse, and transcribe video content. It supports two main operations:

  • Parsing Video Information: Extracts basic metadata and details from a Douyin video URL or shared text containing the video link.
  • Extracting Text (Transcription): Converts the audio of a Douyin video into text using speech recognition models.

Typical use cases include:

  • Automatically retrieving video metadata for cataloging or analysis.
  • Generating transcripts of Douyin videos for accessibility, content indexing, or translation purposes.
  • Integrating Douyin video data into workflows that require video info or textual content extraction.

Example scenarios:

  • A marketing team wants to collect video titles, authors, and descriptions from Douyin links shared in social media.
  • A content creator needs to generate subtitles or searchable text from Douyin videos automatically.

Properties

Name Meaning
操作 (operation) The action to perform on the Douyin video. Options: "解析视频信息" (Parse Video Information), "提取文本" (Extract Text).
视频URL或分享文本 (videoUrl) The full Douyin video URL or a text containing the share link. Example: https://v.douyin.com/xxx or "复制链接打开抖音，直接观看视频！https://v.douyin.com/xxx"
语音识别模型 (recognitionModel) Speech recognition model to use when extracting text. Available options: "Paraformer-V1", "Paraformer-V2", "Fun-ASR". Only shown when operation is "提取文本" (Extract Text).

Output

The node outputs an array of JSON objects, each corresponding to one input item processed. The structure of the json output depends on the selected operation:

  • For 解析视频信息 (Parse Video Information): The output JSON contains the parsed metadata of the Douyin video such as title, author, duration, and other relevant video details extracted from the URL or shared text.
  • For 提取文本 (Extract Text): The output JSON contains the transcription text derived from the video's audio track, generated by the chosen speech recognition model.

No binary data output is indicated by the source code.

Dependencies

  • Requires an API key credential for accessing the Douyin transcript service.
  • Uses external utility functions (parseVideoInfo and extractText) imported from a bundled utils module to perform the core parsing and transcription logic.
  • The speech recognition models referenced are likely provided by an external service (e.g., Aliyun Model Studio), requiring proper API authentication and configuration.

Troubleshooting

  • Unknown Operation Error: If an unsupported operation value is set, the node throws an error like 未知操作: <operation>. Ensure the operation property is correctly set to either "解析视频信息" or "提取文本".
  • Invalid or Missing Video URL: The node requires a valid Douyin video URL or text containing the URL. Providing incorrect or malformed URLs may cause failures in parsing or transcription.
  • API Credential Issues: Since the node depends on an external API credential, missing or invalid credentials will prevent successful execution. Verify that the required API key is configured properly in n8n.
  • Recognition Model Selection: When extracting text, selecting an unsupported or unavailable recognition model might cause errors. Use only the provided options.

Links and References

Discussion