Instagram Reels

Step 1: Extract metadata and audio URL

yt-dlp --write-info-json --skip-download -o "/tmp/reel" "REEL_URL"

This writes /tmp/reel.info.json with the caption, uploader, CDN URLs, and other metadata. No login required for public reels.

Step 2: Download audio and convert to mp3

Extract the audio CDN URL from metadata and download it directly:

AUDIO_URL=$(python3 -c "
import json
d = json.load(open('/tmp/reel.info.json'))
for f in d.get('formats', []):
    if f.get('ext') == 'm4a':
        print(f['url'])
        break
")
curl -sL "$AUDIO_URL" -o /tmp/reel-audio.m4a
ffmpeg -y -i /tmp/reel-audio.m4a -acodec libmp3lame -q:a 4 /tmp/reel-audio.mp3

Step 3: Transcribe with Groq Whisper

curl -s https://api.groq.com/openai/v1/audio/transcriptions \
  -H "Authorization: Bearer $GROQ_API_KEY" \
  -F "file=@/tmp/reel-audio.mp3" \
  -F "model=whisper-large-v3-turbo" \
  -F "response_format=verbose_json"

Returns JSON with text (full transcript) and segments (with timestamps). Language is auto-detected.

Extract caption from metadata

python3 -c "
import json
d = json.load(open('/tmp/reel.info.json'))
print('Caption:', d.get('description', 'No caption'))
print('Author:', d.get('uploader', 'Unknown'))
print('Duration:', round(d.get('duration', 0)), 'seconds')
"

Notes

• Metadata extraction works on public reels without authentication
• For private reels, pass cookies: yt-dlp --cookies /path/to/cookies.txt --write-info-json --skip-download -o "/tmp/reel" "REEL_URL"
• Export cookies with a browser extension like "Get cookies.txt LOCALLY"
• Groq Whisper is free (rate-limited) and returns results in ~1-2 seconds
• Max audio length: 25 minutes per request
• Clean up temp files after: rm -f /tmp/reel.info.json /tmp/reel-audio.*
• Also works with TikTok, YouTube Shorts, and other platforms supported by yt-dlp

Examples

# Full transcription pipeline
yt-dlp --write-info-json --skip-download -o "/tmp/reel" "https://www.instagram.com/reel/ABC123/" && \
AUDIO_URL=$(python3 -c "import json; [print(f['url']) for f in json.load(open('/tmp/reel.info.json')).get('formats',[]) if f.get('ext')=='m4a'][:1]") && \
curl -sL "$AUDIO_URL" -o /tmp/reel-audio.m4a && \
ffmpeg -y -i /tmp/reel-audio.m4a -acodec libmp3lame -q:a 4 /tmp/reel-audio.mp3 2>/dev/null && \
curl -s https://api.groq.com/openai/v1/audio/transcriptions \
  -H "Authorization: Bearer $GROQ_API_KEY" \
  -F "file=@/tmp/reel-audio.mp3" \
  -F "model=whisper-large-v3-turbo" \
  -F "response_format=verbose_json"

# Just get the caption (no transcription)
yt-dlp --write-info-json --skip-download -o "/tmp/reel" "https://www.instagram.com/reel/ABC123/" && \
python3 -c "import json; d=json.load(open('/tmp/reel.info.json')); print(d.get('description',''))"

# Transcribe a TikTok video (same pipeline)
yt-dlp --write-info-json --skip-download -o "/tmp/reel" "https://www.tiktok.com/@user/video/123" && \
AUDIO_URL=$(python3 -c "import json; [print(f['url']) for f in json.load(open('/tmp/reel.info.json')).get('formats',[]) if f.get('ext')=='m4a'][:1]") && \
curl -sL "$AUDIO_URL" -o /tmp/reel-audio.m4a && \
ffmpeg -y -i /tmp/reel-audio.m4a -acodec libmp3lame -q:a 4 /tmp/reel-audio.mp3 2>/dev/null && \
curl -s https://api.groq.com/openai/v1/audio/transcriptions \
  -H "Authorization: Bearer $GROQ_API_KEY" \
  -F "file=@/tmp/reel-audio.mp3" \
  -F "model=whisper-large-v3-turbo" \
  -F "response_format=verbose_json"