원클릭으로
transcribe
Transcribe audio files with speaker diarization via AssemblyAI. Supports local files and Plaud AI cloud recordings.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Transcribe audio files with speaker diarization via AssemblyAI. Supports local files and Plaud AI cloud recordings.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Orchestrate parallel implementation of multiple beads across cmux panes in dependency-aware waves. Use when implementing a whole feature area, dispatching multiple beads at once, or running parallel cld -b sessions. MUST USE when user says "wave", "parallel beads", "implement all beads for X", "start the beads", or references implementing more than 2 beads at once. Also triggers on "cmux dispatch", "multi-bead", "wave orchestrator".
Audit a repo for ADR hoist debt and pre-trinity packages. Triggers on: adr gap, hoist debt, adr audit, pre-trinity packages, architecture drift.
Troubleshoot beads Dolt failures: `bd dolt` push/pull errors, merge conflicts, embedded/shared-server mode problems, remote auth issues, local DB recovery, re-clone, reflog restore, broken `.beads` Dolt config, and brew-services Dolt lifecycle. Use whenever beads sync or Dolt infrastructure is failing — symptoms like "beads do not sync", "cannot push issues", "no common ancestor", "not supported in embedded mode", "Dolt server unreachable", or "lost local database". Read the beads changelog first. Do not use for normal beads tracking (`bd create/ready/close`), standalone Dolt databases, or regular git push/pull.
Create and review agents (subagents). Use when creating specialized AI assistants, reviewing/auditing existing agents, deciding between agent vs skill vs command, or asking about agent best practices, multi-agent pipelines, and model selection. MUST BE USED when the user says "create agent", "new subagent", "review agent", "audit agent", "agent vs skill", or asks about multi-agent architecture.
Query per-bead token cost metrics from the local agent metrics database. Shows cost table, impl:review ratios, most expensive beads, cost trend over time. Triggers on: bead metrics, token cost report, bead costs, /bead-metrics.
Structured 4-stage retrospective for completed beads: Requirements vs Strategy, Strategy vs Execution, Iteration Review, Workflow Audit. Creates Trap/Pattern/Decision artifacts. Use when debriefing a bead, capturing session learnings, or running a compound retrospective.
| name | transcribe |
| description | Transcribe audio files with speaker diarization via AssemblyAI. Supports local files and Plaud AI cloud recordings. |
| triggers | transcribe, transkribiere, transcription, transkription, plaud, diarization, speaker recognition |
| requires_standards | ["english-only"] |
Transcribe audio with speaker diarization via AssemblyAI API. Supports local files and Plaud AI cloud recordings.
# Local file
transcribe ~/recording.mp3
# With language hint
transcribe ~/meeting.mp3 --language de
# Plaud AI: list recordings
transcribe --plaud
# Plaud AI: transcribe specific recording
transcribe --plaud --id a8747e81
After the transcription completes, the CLI outputs the transcript with generic labels (Speaker A, Speaker B, ...) and saves it to ~/.local/share/transcribe/.
Always ask the user:
X Speaker erkannt. Wer ist wer?
- Speaker A: (erster Satz zitieren)
- Speaker B: (erster Satz zitieren)
Once the user provides names, use Edit to replace labels in the saved transcript file:
Speaker A → Malte
Speaker B → Stefan
Replace all occurrences of Speaker A and Speaker B in the saved markdown file.
Alternative: If the user already knows the speakers upfront, pass them directly:
transcribe ~/meeting.mp3 --speakers "Malte,Stefan"
This maps Speaker A → first name, Speaker B → second name (in order of first appearance).
Transcripts are auto-saved to ~/.local/share/transcribe/:
~/.local/share/transcribe/
├── 2026-03-27_combined-recording.md
├── 2026-03-28_besprechung-praxissoftware.md
└── ...
Stored in ~/.config/transcribe/.env (primary) with 1Password fallback:
| Secret | Env Var | 1Password Path |
|---|---|---|
| AssemblyAI API Key | ASSEMBLYAI_API_KEY | op://API Keys/AssemblyAI/API Key |
| Plaud AI Token | PLAUD_TOKEN | op://API Keys/Plaud AI/API Key |
~/.local/bin/transcribe
MP3, WAV, OGG/Opus, M4A, FLAC, WebM, MP4 (audio track)
a8747e81 matches full UUID)