Gettr Transcribe (MLX Whisper)

Quick start

# 1. Parse the slug from the URL (just read it — no script needed)
#    https://gettr.com/post/p1abc2def  → slug = p1abc2def
#    https://gettr.com/streaming/p3xyz → slug = p3xyz

# 2. Get the audio/video URL via browser automation (see Step 1 below)
#    For /streaming/ URLs: extract the .m4a audio URL
#    For /post/ URLs: extract the og:video .m3u8 URL

# 3. Run download + transcription pipeline
bash scripts/run_pipeline.sh "<AUDIO_OR_VIDEO_URL>" "<SLUG>"

To explicitly set the transcription language (recommended for non-English content):

bash scripts/run_pipeline.sh --language zh "<AUDIO_OR_VIDEO_URL>" "<SLUG>"

Common language codes: zh (Chinese), en (English), ja (Japanese), ko (Korean), es (Spanish), fr (French), de (German), ru (Russian).

This outputs:

• ./out/gettr-transcribe/<slug>/audio.wav
• ./out/gettr-transcribe/<slug>/audio.vtt

Summarization is handled separately by the caller (see your prompt for summarization instructions).

Workflow (GETTR URL → transcript)

Inputs to confirm

Ask for:

• GETTR post URL
• Language (optional): if the video is non-English and auto-detection fails, ask for the language code (e.g., zh for Chinese)

Notes:

• This skill does not handle authentication-gated GETTR posts.
• This skill does not translate; outputs stay in the video's original language.
• If transcription quality is poor or mixed with English, re-run with explicit --language flag.

Prereqs (local)

• mlx_whisper installed and on PATH
• ffmpeg installed (recommended: brew install ffmpeg)

Step 0 — Parse the slug and pick an output directory

Parse the slug directly from the GETTR URL — just read the last path segment, no script needed:

• https://gettr.com/post/p1abc2def → slug = p1abc2def
• https://gettr.com/streaming/p3xyz789 → slug = p3xyz789

Output directory: ./out/gettr-transcribe/<slug>/

Directory structure:

• ./out/gettr-transcribe/<slug>/audio.wav
• ./out/gettr-transcribe/<slug>/audio.vtt

Step 1 — Get the audio/video URL via browser automation

Use browser automation to navigate to the GETTR URL and extract the media URL from the rendered DOM.

For /streaming/ URLs (primary path)

Streaming pages provide a direct .m4a audio download. Extract it by deriving from the og:video meta tag:

1. Navigate to the GETTR streaming URL and wait for the page to fully load (JavaScript must execute)
2. Extract the audio URL via JavaScript:

   const ogVideo = document.querySelector('meta[property="og:video"]')?.getAttribute("content");
   // Replace .m3u8 with /audio.m4a to get the direct audio download URL
   const audioUrl = ogVideo.replace(".m3u8", "/audio.m4a");
   

3. Use the .m4a URL for the pipeline in Step 2

The .m4a URL is a direct file download (no HLS), so it downloads faster and more reliably than the .m3u8 stream.