x-video-transcribe

What This Skill Does

The x-video-transcribe skill is a robust automation tool designed to bridge the gap between multimedia content on X (formerly Twitter) and readable, searchable text. It automates the complex workflow of fetching, extracting, and processing video content. By leveraging the bird CLI, the skill identifies video assets within a tweet, downloads the source file, and uses ffmpeg to isolate the audio stream. This audio is then processed through Google's Gemini-2.0-flash model, which provides high-fidelity speech-to-text conversion and contextual summarization. This tool is essential for users who need to digest video-heavy social media content without the time commitment of watching full-length clips, making it a critical asset for researchers, journalists, and power users.

Installation

To integrate this skill into your environment, use the OpenClaw command-line interface. Ensure you have the necessary dependencies—ffmpeg and the bird CLI—installed on your host machine before proceeding. Run the following command in your terminal:

clawhub install openclaw/skills/skills/henrino3/ec-x-video-transcribe

After installation, verify that your configuration files are correctly pointing to your credentials. You must provide a valid GEMINI_API_KEY as an environment variable and ensure your bird CLI cookies are authenticated at the path defined in your BIRD_ENV configuration.

Use Cases

This skill is ideal for:

• Analyzing long-form video interviews posted on X.
• Summarizing breaking news video clips for quick documentation.
• Converting audio-based video content into markdown notes for knowledge management.
• Extracting insights from tech tutorials or product announcements shared via video.

Example Prompts

1. "Can you transcribe this video for me? Here is the link: https://x.com/tech_expert/status/123456"
2. "Please provide a detailed summary of the main points made in this video: https://x.com/news_outlet/status/789012"
3. "Transcribe the following tweet video and save the results to my docs folder: https://x.com/creator/status/345678"

Tips & Limitations

• Rate Limiting: Be aware of X's API constraints and Gemini's tier limits. Running high volumes of transcriptions in a short window may trigger rate-limiting.
• Audio Quality: Transcription accuracy is highly dependent on the quality of the original audio. Background music or poor recording quality can decrease the accuracy of the Gemini model.
• Authentication: Always keep your bird.env file secured; it contains sensitive cookies required for accessing private or protected content.
• File Management: For very long videos, ensure you have sufficient disk space for the temporary audio extraction process.