ASR Transcribe to Text
Transcribe audio and video to text with Qwen3-ASR — local MLX inference on Apple Silicon (no API key, 15–27x realtime) or a remote API endpoint, auto-detecting the best path.
Recordings, lectures, and meetings pile up untranscribed because cloud ASR is costly or private. This playbook transcribes locally on Apple Silicon — fast, free, and offline.
Who it's for: podcasters, researchers, students, journalists, note-takers
Example
"Transcribe this 1-hour interview recording" → A full text transcript produced locally at 15–27x realtime, no API key needed
CLAUDE.md Template
New here? 3-minute setup guide → | Already set up? Copy the template below.
npx ccplaybooks add asr-transcribe-to-text# ASR Transcribe to Text
Transcribe audio/video files to text using Qwen3-ASR. Two inference paths:
| Mode | When | Speed | Cost |
|------|------|-------|------|
| **Local MLX** | macOS Apple Silicon | 15-27x realtime | Free |
| **Remote API** | Any platform, or when local unavailable | Depends on GPU | API/self-hosted |
Configuration persists in `${CLAUDE_PLUGIN_DATA}/config.json`.
## Step 0: Detect Platform and Load ConfigGet new playbooks like this one
One email a week with new Claude Code workflows. Free, like everything here.
No spam. Unsubscribe anytime.
What This Does
Transcribe audio and video to text with Qwen3-ASR — local MLX inference on Apple Silicon (no API key, 15–27x realtime) or a remote API endpoint, auto-detecting the best path.
What's Inside
The template covers:
- Step 0: Detect Platform and Load Config
- Step 1: Extract Audio (if input is video)
- Step 2: Transcribe
- Step 3: Verify Output
- Step 4: Fallback — Overlap-Merge (Remote API Only)
- Step 5: Recommend Transcript Correction
Quick Start
Step 1: Create a Project Folder
Make a dedicated folder for this workflow and open it in Claude Code.
Step 2: Download the Template
Click Download above to save the template, then drop it into your project as CLAUDE.md (or paste it into your existing one).
Step 3: Start Working
Tell Claude what you need in plain language — it will follow the template's workflow automatically. For example:
Transcribe this 1-hour interview recording
Claude reads the template and runs the steps for you.