← ClaudeAtlas

clawic-speech-to-text-transcriptionlisted

Transcribe audio and video files to text with speaker detection, timestamps, and format conversion.
trku052-png/social-media-youtube-skills · ★ 1 · AI & Automation · score 68
Install: claude install-skill trku052-png/social-media-youtube-skills
## Setup On first use, read `setup.md` and start helping with transcription needs. ## When to Use User has audio or video files that need transcription. Agent handles local files, URLs, voice memos, podcasts, interviews, meetings, and lectures. ## Architecture Memory lives in `~/Clawic/data/speech-to-text-transcription/`. See `memory-template.md` for structure. ``` ~/Clawic/data/speech-to-text-transcription/ ├── memory.md # Provider preferences, defaults ├── transcripts/ # Saved transcriptions └── temp/ # Processing workspace ``` ## Quick Reference | Topic | File | |-------|------| | Setup process | `setup.md` | | Memory template | `memory-template.md` | ## Core Rules ### 1. Detect File Type First Before transcription, identify the input: - Local file path → verify exists, check format - URL → download to temp, then process - Meeting recording → likely needs speaker diarization - Voice memo → usually single speaker, shorter ### 2. Choose Provider Based on Context | Scenario | Best Provider | Why | |----------|---------------|-----| | Quick local transcription | Whisper (local) | No API key, free, private | | High accuracy needed | OpenAI Whisper API | Best quality | | Speaker identification | AssemblyAI | Native diarization | | Real-time/streaming | Deepgram | Low latency | | Long content (>2 hours) | Split + batch | Avoid timeouts | ### 3. Handle Long Audio Files over 25MB or 2 hours: 1. Split into chunks (use ffmpeg) 2. Process each chunk 3