Whisper Transcription Playbooks

SkillDev tools

Use this skill when the task involves speech-to-text, audio note transcription, or voice-to-text workflows.

Available today. Use it from your connected AI after setup.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the Whisper Transcription Playbooks skill

About this skill

Self-hosted AI workspace where chat becomes visual workflows, multi-agent operations, and reviewable automations. Local memory; local or cloud models

What this skill tells your AI

The instructions your AI receives, as published by aaronnat23/disp8ch in optional-skills/whisper-transcription-playbooks/SKILL.md and read by ahel’s review.

Use this skill when the task involves speech-to-text, audio note transcription, or voice-to-text workflows.

Use when

  • The user wants to turn audio or voice messages into reliable text.
  • A voice workflow should be validated end to end before broader automation depends on it.
  • The task needs guidance around transcript quality, timestamps, or follow-up summaries.

Workflow

  1. Confirm the audio source, language, and expected output format.
  2. Distinguish transcript generation from later summarization or action extraction.
  3. Call out quality risks early: noisy audio, speaker overlap, missing punctuation, or missing timestamps.
  4. Keep the first validation small so setup failures are easy to isolate.
  5. Return both the raw transcription outcome and any cleaned follow-up summary separately.

Deliverable

  • Input assumptions.
  • Transcription checklist.
  • Quality risks.
  • Suggested validation and follow-up summary shape.

Signals

GitHub stars
100
Forks
2
Last commit
Sep 2026
Advanced
Item type
skill
Key
whisper-transcription-playbooks
Source
github.com/aaronnat23/disp8ch