podcast-transcript-fetcher
installsforks
How to install podcast-transcript-fetcher?
varnan-tech/opendirectory/podcast-transcript-fetcher
$npx -y skills add Varnan-Tech/opendirectory --skill podcast-transcript-fetcherUse when fetching, searching, or analyzing transcripts from Lenny's Podcast, Dwarkesh Podcast, Cheeky Pint, 20VC, or A16z Podcast. Tier 2 (RSS+Groq Whisper) is the recommended approach -- fast, free, and most reliable. Also use when asked to "get transcript", "find episode", "sum
SKILL.md
| 1 | # Podcast Transcript Fetcher |
| 2 | |
| 3 | Fetch transcripts from 5 supported podcasts. **Tier 2 (RSS+Groq Whisper) is the recommended approach** -- fast, free, and the most reliable across all podcasts. Tier 1 free sources are best-effort (limited availability). Tier 3 Taddy API is the premium/commercial option. |
| 4 | |
| 5 | ## Quick Reference |
| 6 | |
| 7 | ```bash |
| 8 | # Get latest episode transcript (auto-detects best method) |
| 9 | python scripts/get_transcript.py "Lenny's Podcast" --latest |
| 10 | |
| 11 | # Search by episode title or number |
| 12 | python scripts/get_transcript.py 20vc --episode "Marc Andreessen" |
| 13 | python scripts/get_transcript.py dwarkesh --episode 15 |
| 14 | |
| 15 | # Force specific method |
| 16 | python scripts/get_transcript.py "cheeky pint" --latest --method whisper |
| 17 | python scripts/get_transcript.py a16z --latest --method taddy |
| 18 | |
| 19 | # Save to file |
| 20 | python scripts/get_transcript.py lennys --latest --output transcript.md |
| 21 | |
| 22 | # List all supported podcasts |
| 23 | python scripts/get_transcript.py --list-podcasts |
| 24 | ``` |
| 25 | |
| 26 | ## Supported Podcasts |
| 27 | |
| 28 | | Podcast | Tier 1 (best-effort) | Tier 2 RSS+Whisper [RECOMMENDED] | Tier 3 Taddy (premium) | |
| 29 | |---------|---------------------|-----------------------------------|------------------------| |
| 30 | | Lenny's Podcast | GitHub archive (269 transcripts) | ✅ Substack RSS | ✅ Covered | |
| 31 | | Dwarkesh Podcast | Website scrape + Substack PDF | ✅ Substack RSS | ✅ Covered | |
| 32 | | Cheeky Pint | (none) | ✅ Transistor.fm RSS | ✅ Covered | |
| 33 | | 20VC | Substack PDF | ✅ Libsyn RSS | ✅ Covered | |
| 34 | | A16z Podcast | Website scrape | ✅ Simplecast RSS | ✅ Covered | |
| 35 | |
| 36 | ## Implementation |
| 37 | |
| 38 | ### 1. Install Dependencies |
| 39 | |
| 40 | ```bash |
| 41 | # Core (always required) |
| 42 | pip install requests |
| 43 | |
| 44 | # Cloud transcription (recommended — fast, free tier) |
| 45 | pip install groq |
| 46 | export GROQ_API_KEY="your-key" # Get at https://console.groq.com |
| 47 | |
| 48 | # Local transcription (free, needs ~5GB RAM) |
| 49 | pip install faster-whisper |
| 50 | |
| 51 | # Audio compression (for Groq's 25 MB limit — Windows: winget/scoop) |
| 52 | # winget install ffmpeg or scoop install ffmpeg |
| 53 | |
| 54 | # Taddy API (commercial, optional) |
| 55 | export TADDY_API_KEY="your-key" # Get at https://taddy.org |
| 56 | ``` |
| 57 | |
| 58 | ### 2. Get a Transcript |
| 59 | |
| 60 | The script auto-selects the best method. **Tier 2 is the default recommendation:** |
| 61 | |
| 62 | ``` |
| 63 | Tier 1 → Tier 2 (RECOMMENDED) → Tier 3 |
| 64 | (best-effort) (Whisper) (Taddy API premium) |
| 65 | ``` |
| 66 | |
| 67 | **Tier 1: Free direct sources (best-effort, limited availability)** |
| 68 | - Lenny's: Clones `ChatPRD/lennys-podcast-transcripts` and searches by title |
| 69 | - Dwarkesh: Substack PDF scrape |
| 70 | - 20VC: Substack PDF scrape |
| 71 | - A16z: Website scrape |
| 72 | - Cheeky Pint: No Tier 1 sources available |
| 73 | - Note: Tier 1 sources are best-effort and limited. Tier 2 (RSS+Whisper) is the recommended approach. |
| 74 | |
| 75 | **Tier 2: RSS + Whisper transcription [RECOMMENDED]** |
| 76 | - Downloads MP3 from podcast RSS feed |
| 77 | - Compresses if >25 MB (ffmpeg) |
| 78 | - Transcribes via Groq Whisper API (free tier, ~10s per hour of audio) |
| 79 | - Fast, free, and works for every podcast in the registry |
| 80 | - Default recommendation for all use cases |
| 81 | |
| 82 | **Tier 3: Taddy API (commercial/premium)** |
| 83 | - Requires `TADDY_API_KEY` ($75/mo+) |
| 84 | - Use for large-scale or production transcript needs |
| 85 | - Covers all 5 podcasts with auto-transcription |
| 86 | |
| 87 | ### 3. Analyze with AI |
| 88 | |
| 89 | Once you have a transcript, pipe it to the agent for analysis: |
| 90 | |
| 91 | ```markdown |
| 92 | I have this transcript from [podcast]. Can you: |
| 93 | 1. Summarize the key arguments |
| 94 | 2. Extract 3 actionable insights |
| 95 | 3. Identify any controversial claims |
| 96 | 4. Compare with [other podcast] on the same topic |
| 97 | ``` |
| 98 | |
| 99 | ## Supported Workflows |
| 100 | |
| 101 | ### Single Episode |
| 102 | |
| 103 | | Scenario | Command | |
| 104 | |----------|---------| |
| 105 | | Latest episode | `get_transcript.py "Lenny's Podcast" --latest` | |
| 106 | | Specific episode by title | `get_transcript.py 20vc --episode "Sam Altman"` | |
| 107 | | Episode by number | `get_transcript.py dwarkesh --episode 42` | |
| 108 | | Force Whisper transcription (Tier 2, recommended) | `get_transcript.py a16z --latest --method whisper` | |
| 109 | | Force Taddy API (premium) | `get_transcript.py lennys --latest --method taddy` | |
| 110 | | Save to Markdown | `get_transcript.py cheeky-pint --latest --output episode.md` | |
| 111 | | JSON output | `get_transcript.py dwarkesh --latest --json` | |
| 112 | |
| 113 | ### Cross-Podcast Search & Batch |
| 114 | |
| 115 | | Scenario | Command | |
| 116 | |----------|---------| |
| 117 | | Search all podcasts by keyword | `get_transcript.py --search "Marc Andreessen"` | |
| 118 | | Search by guest name | `get_transcript.py --guest "Sam Altman"` | |
| 119 | | Search within one podcast | `get_transcript.py "Lenny's Podcast" --search "vibe coding"` | |
| 120 | | Batch-transcribe last N episodes | `get_transcript.py "Dwarkesh Podcast" --last 5` | |
| 121 | | Search + transcribe top matches | `get_transcript.py --search "AI |
People who liked this also viewed
6 picksType
- seo-auditWhen the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tagSkillsJul 2026
- copywritingWhen the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages, or product pages. Also use when the user sSkillsJul 2026
- marketing-psychologyWhen the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,'SkillsJul 2026
- content-strategyWhen the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover. Also use when the user mentions "content strategy," "what should I write about," "conSkillsJul 2026
- programmatic-seoWhen the user wants to create SEO-driven pages at scale using templates and data. Also use when the user mentions "programmatic SEO," "template pages," "pages at scale," "directory pages," "location pSkillsJul 2026
- marketing-ideasWhen the user needs marketing ideas, inspiration, or strategies for their SaaS or software product. Also use when the user asks for 'marketing ideas,' 'growth ideas,' 'how to market,' 'marketing stratSkillsJul 2026
