skills.rest
Xiaon-Junf
Xiaon-JunfCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

toefl-listen-repeat-extractor

Extract TOEFL Listen & Repeat sentences and align them to audio with whisper.cpp.

2|Updated May 18, 2026
Search Tags:#batch processing#whisper.cpp#anki#csv export#toefl#listen and repeat#audio alignment
One-click install
npx skills add https://github.com/Xiaon-Junf/Anki_toefl_listen_repeat_extractor_skill --skill toefl-listen-repeat-extractor
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: toefl-listen-repeat-extractor
Source: https://github.com/Xiaon-Junf/Anki_toefl_listen_repeat_extractor_skill/tree/main
Command: npx skills add https://github.com/Xiaon-Junf/Anki_toefl_listen_repeat_extractor_skill --skill toefl-listen-repeat-extractor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This skill removes the manual, error-prone work of matching TOEFL Speaking “Listen & Repeat” answers to the correct audio segments and converting them into Anki-ready flashcards.

Core Features & Use Cases

  • Answer-driven sentence extraction: Extracts the exact repeat sentences from TOEFL answer PDFs/DOCX/TXT instead of relying on ASR segmentation guesses.
  • Word-timestamp alignment with whisper.cpp: Uses whisper.cpp to generate word-level timestamps, then aligns each extracted answer sentence to the most accurate time span.
  • Automatic clip + Anki CSV generation: Cuts one audio clip per sentence and exports an Anki import CSV referencing each clip via [sound:filename.mp3].
  • Batch processing across exam folders: Runs over a directory of multiple exam folders, producing per-exam outputs plus an optional combined CSV.

Quick Start

Tell your Agent to run this skill on an exam root folder that contains TOEFL Speaking audio files and their corresponding answer files to produce an Anki CSV with one clip per “Listen & Repeat” sentence.

Frequently Asked Questions about toefl-listen-repeat-extractor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract TOEFL Listen and Repeat sentences from answer PDFs and align them with audio?▼

Extracting TOEFL Listen and Repeat sentences from answer PDFs, DOCX, or TXT files uses whisper.cpp word-level timestamps to align each extracted answer sentence to the correct audio segment, ensuring accurate matching without relying on ASR segmentation guesses.

Can I batch process multiple TOEFL exam folders to generate Anki cards automatically?▼

Batch processing TOEFL exam folders supports directories containing multiple exams, producing per-exam audio clips and Anki import CSV rows, plus an optional combined CSV for all extracted Listen and Repeat sentences.

Does this tool require external command-line tools like ffmpeg and whisper.cpp to cut audio clips?▼

Cutting per-sentence audio clips requires ffmpeg and whisper.cpp external command-line tools to transcribe audio, generate word timestamps, align sentences deterministically, and export Anki-ready files.

What is the best way to turn TOEFL Speaking audio into Anki spaced-repetition flashcards?▼

Turning TOEFL Speaking audio into Anki flashcards is best done by extracting exact repeat sentences from answer files, aligning them with whisper.cpp timestamps, and exporting CSV rows referencing individual audio clips via [sound:filename.mp3].

Do I need to manually copy audio clips to Anki collection.media after CSV export?▼

Copying audio clips to Anki collection.media is supported as an optional step during export, allowing the generated CSV to reference clips immediately without manual file transfers.

Why does ASR segmentation alone fail to match TOEFL Listen and Repeat sentences accurately?▼

ASR segmentation alone fails to match TOEFL Listen and Repeat sentences accurately because it guesses sentence boundaries, whereas answer-driven extraction pulls exact sentences from PDFs or DOCX and aligns them using whisper.cpp word timestamps for precise time spans.

Related Skills

Explore More Education & Research Skills→
maxgent-aimaxgent-ai

audio-transcribe

Transcribe audio and video files with word-level timestamps using WhisperX.

Official
Advanced
TaylorHustonTaylorHuston
69

study-notes

Generate structured study notes with theory, examples, and flashcards.

Community
Basic
jingx8885jingx8885
2

japanese-deep-translate

Generate interactive Japanese study pages with sentence breakdowns and audio.

Community
Advanced
dbbaskettedbbaskette

voice-handling

Transcribe on-device audio to text using a local Whisper pipeline.

Community
Intermediate