Asr Transcribe To Text

Transcribes audio and video to text using Qwen3-ASR with two paths: local MLX inference on Apple Silicon Macs (15-27x realtime, no API key) or remote API for other platforms. The skill auto-detects your hardware and recommends the best mode, handles long recordings without truncation (a common gotcha with the default max_tokens setting), and includes fallback chunking strategies when needed. Works with meetings, lectures, podcasts, screen recordings, anything you want converted to text. The bundled scripts handle extraction, model loading, and cleanup. After transcription it prompts you to run a separate fixer skill since raw ASR output always has recognition errors. Solid choice if you need offline transcription on Mac or want to point at your own vLLM server.

skills.sh installs: 1.7K
GitHub stars: 1.5K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add daymade/claude-code-skills --skill asr-transcribe-to-text --agent claude-code

Installs into .claude/skills of the current project.

Files

ASR Transcribe to Text

Transcribe audio/video to speaker-labeled text. Local execution has two explicit routes. Long or unattended recordings use checkpointed whisper.cpp + Silero VAD blocks, then late-fuse pyannote speakers. Short/medium recordings may use the Qwen3-ASR + mlx-whisper alignment route. Neither route cuts ASR input at diarization turns; speaker attribution happens after continuous-context ASR.

Route before ASR: the transcript is the result, not the run

Preserve course videos before choosing an ASR route. When uploading a course video, or when the user requires the picture or original media, upload the original video file with its picture, audio and original speed. Skip Step 2 and the preprocessing section unless the user explicitly requests conversion. An existing transcript can satisfy the text request but does not satisfy an outstanding video upload. Slow transfers or upload failures do not authorize extracting audio, transcoding or speeding up the video.

SKILL.md on GitHub

Details

Repository: github.com/daymade/claude-code-skills
Categories: Git & Pull Requests, Code Review & Quality, Generative Media, Video & Audio Editing
First seen: Jun 3, 2026