audio-transcriber
starsforks
How to install audio-transcriber?
samarthakv29/antigravity-god-mode/audio-transcriber
$npx -y skills add SamarthaKV29/antigravity-god-mode --skill audio-transcriberTransform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration
SKILL.md
| 1 | ## Purpose |
| 2 | |
| 3 | This skill automates audio-to-text transcription with professional Markdown output, extracting rich technical metadata (speakers, timestamps, language, file size, duration) and generating structured meeting minutes and executive summaries. It uses Faster-Whisper or Whisper with zero configuration, working universally across projects without hardcoded paths or API keys. |
| 4 | |
| 5 | Inspired by tools like Plaud, this skill transforms raw audio recordings into actionable documentation, making it ideal for meetings, interviews, lectures, and content analysis. |
| 6 | |
| 7 | ## When to Use |
| 8 | |
| 9 | Invoke this skill when: |
| 10 | |
| 11 | - User needs to transcribe audio/video files to text |
| 12 | - User wants meeting minutes automatically generated from recordings |
| 13 | - User requires speaker identification (diarization) in conversations |
| 14 | - User needs subtitles/captions (SRT, VTT formats) |
| 15 | - User wants executive summaries of long audio content |
| 16 | - User asks variations of "transcribe this audio", "convert audio to text", "generate meeting notes from recording" |
| 17 | - User has audio files in common formats (MP3, WAV, M4A, OGG, FLAC, WEBM) |
| 18 | |
| 19 | ## Workflow |
| 20 | |
| 21 | ### Step 0: Discovery (Auto-detect Transcription Tools) |
| 22 | |
| 23 | **Objective:** Identify available transcription engines without user configuration. |
| 24 | |
| 25 | **Actions:** |
| 26 | |
| 27 | Run detection commands to find installed tools: |
| 28 | |
| 29 | ```bash |
| 30 | # Check for Faster-Whisper (preferred - 4-5x faster) |
| 31 | if python3 -c "import faster_whisper" 2>/dev/null; then |
| 32 | TRANSCRIBER="faster-whisper" |
| 33 | echo "✅ Faster-Whisper detected (optimized)" |
| 34 | # Fallback to original Whisper |
| 35 | elif python3 -c "import whisper" 2>/dev/null; then |
| 36 | TRANSCRIBER="whisper" |
| 37 | echo "✅ OpenAI Whisper detected" |
| 38 | else |
| 39 | TRANSCRIBER="none" |
| 40 | echo "⚠️ No transcription tool found" |
| 41 | fi |
| 42 | |
| 43 | # Check for ffmpeg (audio format conversion) |
| 44 | if command -v ffmpeg &>/dev/null; then |
| 45 | echo "✅ ffmpeg available (format conversion enabled)" |
| 46 | else |
| 47 | echo "ℹ️ ffmpeg not found (limited format support)" |
| 48 | fi |
| 49 | ``` |
| 50 | |
| 51 | **If no transcriber found:** |
| 52 | |
| 53 | Offer automatic installation using the provided script: |
| 54 | |
| 55 | ```bash |
| 56 | echo "⚠️ No transcription tool found" |
| 57 | echo "" |
| 58 | echo "🔧 Auto-install dependencies? (Recommended)" |
| 59 | read -p "Run installation script? [Y/n]: " AUTO_INSTALL |
| 60 | |
| 61 | if [[ ! "$AUTO_INSTALL" =~ ^[Nn] ]]; then |
| 62 | # Get skill directory (works for both repo and symlinked installations) |
| 63 | SKILL_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)" |
| 64 | |
| 65 | # Run installation script |
| 66 | if [[ -f "$SKILL_DIR/scripts/install-requirements.sh" ]]; then |
| 67 | bash "$SKILL_DIR/scripts/install-requirements.sh" |
| 68 | else |
| 69 | echo "❌ Installation script not found" |
| 70 | echo "" |
| 71 | echo "📦 Manual installation:" |
| 72 | echo " pip install faster-whisper # Recommended" |
| 73 | echo " pip install openai-whisper # Alternative" |
| 74 | echo " brew install ffmpeg # Optional (macOS)" |
| 75 | exit 1 |
| 76 | fi |
| 77 | |
| 78 | # Verify installation succeeded |
| 79 | if python3 -c "import faster_whisper" 2>/dev/null || python3 -c "import whisper" 2>/dev/null; then |
| 80 | echo "✅ Installation successful! Proceeding with transcription..." |
| 81 | else |
| 82 | echo "❌ Installation failed. Please install manually." |
| 83 | exit 1 |
| 84 | fi |
| 85 | else |
| 86 | echo "" |
| 87 | echo "📦 Manual installation required:" |
| 88 | echo "" |
| 89 | echo "Recommended (fastest):" |
| 90 | echo " pip install faster-whisper" |
| 91 | echo "" |
| 92 | echo "Alternative (original):" |
| 93 | echo " pip install openai-whisper" |
| 94 | echo "" |
| 95 | echo "Optional (format conversion):" |
| 96 | echo " brew install ffmpeg # macOS" |
| 97 | echo " apt install ffmpeg # Linux" |
| 98 | echo "" |
| 99 | exit 1 |
| 100 | fi |
| 101 | ``` |
| 102 | |
| 103 | This ensures users can install dependencies with one confirmation, or opt for manual installation if preferred. |
| 104 | |
| 105 | **If transcriber found:** |
| 106 | |
| 107 | Proceed to Step 0b (CLI Detection). |
| 108 | |
| 109 | |
| 110 | ### Step 1: Validate Audio File |
| 111 | |
| 112 | **Objective:** Verify file exists, check format, and extract metadata. |
| 113 | |
| 114 | **Actions:** |
| 115 | |
| 116 | 1. **Accept file path or URL** from user: |
| 117 | - Local file: `meeting.mp3` |
| 118 | - URL: `https://example.com/audio.mp3` (download to temp directory) |
| 119 | |
| 120 | 2. **Verify file exists:** |
| 121 | |
| 122 | ```bash |
| 123 | if [[ ! -f "$AUDIO_FILE" ]]; then |
| 124 | echo "❌ File not found: $AUDIO_FILE" |
| 125 | exit 1 |
| 126 | fi |
| 127 | ``` |
| 128 | |
| 129 | 3. **Extract metadata** using ffprobe or file utilities: |
| 130 | |
| 131 | ```bash |
| 132 | # Get file size |
| 133 | FILE_SIZE=$(du -h "$AUDIO_FILE" | cut -f1) |
| 134 | |
| 135 | # Get duration and format using ffprobe |
| 136 | DURATION=$(ffprobe -v error -show_entries format=duration \ |
| 137 | -of default=noprint_wrappers=1:nokey=1 "$AUDIO_FILE" 2>/dev/null) |
| 138 | FORMAT=$(ffprobe -v error -select_streams a:0 -show_entries \ |
| 139 | stream=codec_name -of default=noprint_wrappers=1:nokey=1 "$AUDIO_FILE" 2>/dev/null) |
| 140 | |
| 141 | # Convert duration to HH: |
People who liked this also viewed
6 picksType
- entra-app-registrationGuides Microsoft Entra ID app registration, OAuth 2.0 authentication, and MSAL integration. USE FOR: create app registration, register Azure AD app, configure OAuth, set up authentication, add API perSkillsJul 2026
- azure-complianceRun Azure compliance and security audits with azqr plus Key Vault expiration checks. Covers best-practice assessment, resource review, policy/compliance validation, and security posture checks. WHEN: SkillsJul 2026
- azure-rbacOfficial agent plugin providing skills and MCP server configurations for Azure scenarios.SkillsJul 2026
- better-auth-best-practicesAgent skill from better-auth/skillsSkillsJul 2026
- firebase-security-rules-auditorA skill to evaluate how secure Firestore security rules are. Use this when Firestore security rules are updated to ensure that the generated rules are extremely secure and robust.SkillsJul 2026
- audit-websiteAudit a website with the squirrelscan CLI and fix the findings in code. Runs SEO, performance, security, technical, content, accessibility, and 15 other rule categories (260+ rules), returns an LLM-opSkillsJul 2026
