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 (the Chinese version of TikTok) videos. It provides tools to download, parse, and transcribe Douyin videos by extracting their basic information or converting the audio content into text transcripts. This can be particularly useful for content creators, marketers, or analysts who want to automate the processing of Douyin video data, such as retrieving metadata or generating subtitles and searchable text from videos.

Common scenarios include:

  • Extracting video metadata like title, author, and statistics for cataloging or analysis.
  • Transcribing spoken content in Douyin videos to text for accessibility, translation, or content repurposing.
  • Automating workflows that require video content understanding without manual intervention.

Properties

Name Meaning
视频URL或分享文本 The complete URL of the Douyin video or a text containing the share link. For example: https://v.douyin.com/xxx or a copied share message including the link.
操作 (operation) The action to perform on the video. Options are:
- 解析视频信息 (parseVideoInfo): Parse basic video information.
- 提取文本 (extractText): Convert the video’s audio to text transcript.
语音识别模型 (recognitionModel) The speech recognition model to use when extracting text. Available options:
- Paraformer-V1
- Paraformer-V2 (default)
- Fun-ASR

Output

The node outputs an array of JSON objects, each corresponding to one input item processed. Each output JSON contains the result of the selected operation:

  • For 解析视频信息 (parseVideoInfo): The JSON includes parsed metadata about the Douyin video such as title, author, duration, and other relevant details extracted from the video URL.
  • For 提取文本 (extractText): The JSON contains the transcribed text converted from the video's audio track using the selected 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.
  • Depends on external utility functions (parseVideoInfo and extractText) imported from a bundled utility module.
  • The speech recognition models reference an external service documented at Aliyun Model Studio (https://help.aliyun.com/zh/model-studio/recording-file-recognition).
  • Proper network access and valid credentials are necessary to call the Douyin transcript API.

Troubleshooting

  • Unknown Operation Error: If an unsupported operation is specified, the node throws an error indicating "Unknown operation". Ensure the operation property is set to either "parseVideoInfo" or "extractText".
  • Invalid or Missing Video URL: The node requires a valid Douyin video URL or share text containing the URL. Incorrect or malformed URLs will cause failures in parsing or transcription.
  • API Authentication Failures: Missing or invalid API credentials will prevent the node from accessing the Douyin transcript service. Verify that the required API key is configured correctly.
  • Recognition Model Issues: When extracting text, selecting an unsupported or unavailable recognition model may lead to errors. Use one of the provided options.
  • Network or Service Errors: Connectivity issues or service downtime can cause execution failures. Check network status and API service availability.

Links and References

Discussion