Agent skill · writing content · daymade
asr-transcribe-to-text
Transcribes audio or video to speaker-labeled, timestamped text, locally with MLX on Apple Silicon or remotely. Use for 转录 / 录音转文字 / 说话人分离 / 字幕, and also for preparing audio for ASR without transcribing: 转格式, 降采样到 16kHz, merging recorder segments, or compressing and speeding up audio before 飞书妙记 — even when it looks like a one-line ffmpeg job.
Why this skill is useful
Adds executable scripts for audio preprocessing and ASR transcription that enhance capabilities beyond standard practices.
What it needs
Requires ffmpeg, python3 installed locally. Requires huggingface account access. About 11k tokens when loaded. Last updated 2026-08-07. 1,320 stars on the source repository.
What this skill does
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. Apply original-speed requirements to audio as well. For an original-file or original-speed upload request, upload a compatible original directly. If merging or format conversion is needed and permitted, keep 1.0x speed and the original source-time mapping. Use 1.0x for playback/speaker review against the original media unless the user permits a time-mapped derivative. Metered billing alone does not authorize speedup; follow the preprocessing conditions below. Before starting transcription, check the owning project's transcript catalog, external source index, and declared prior-work carriers for an existing canonical transcript using source ID, date, title, and entity terms. A verified human-reviewed/current transcript ends transcription unless the user explicitly asked for a new independent comparison. Raw audio existing is not a reason to regenerate text that already exists. When no canonical transcript exists: 1. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills daymade/asr-transcribe-to-text