word-timestamps-extractor

Extract word-level timestamps from audio using faster-whisper or OpenAI Whisper.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/bachdyon/video-automator-skills --skill word-timestamps-extractor
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: word-timestamps-extractor
Source: https://github.com/bachdyon/video-automator-skills/tree/main/skills/word-timestamps-extractor
Command: npx skills add https://github.com/bachdyon/video-automator-skills --skill word-timestamps-extractor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires faster-whisper, openai-whisper, pyparsing, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of extracting word-level timestamps from audio, providing accurate timing for transcripts which is essential for subtitle creation and semantic asset mapping.

Core Features & Use Cases

  • Word-Level Timestamp Extraction: Accurately identifies when each word is spoken in an audio clip.
  • Language Support: Handles Vietnamese and other languages.
  • Transcript Generation: Outputs a TOML file with detailed timing information for each word and sentence.
  • Use Case: For video editors working with Vietnamese content, this Skill can help ensure that subtitles perfectly synchronize with the audio.

Quick Start

Use the word-timestamps-extractor skill to generate word timestamps for the audio file 'source/voice.wav'.

Frequently Asked Questions about word-timestamps-extractor

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

FAQPage Schema
How do I extract word-level timestamps from audio for subtitle synchronization?

To extract word-level timestamps for subtitle synchronization, you can use this Skill to process audio files with faster-whisper or OpenAI Whisper, generating a TOML file containing precise timing details for each spoken word and sentence.

Does faster-whisper support word timing extraction for Vietnamese audio content?

Yes, faster-whisper supports word timing extraction for Vietnamese audio content. This Skill leverages faster-whisper or OpenAI Whisper to accurately identify when each word is spoken, making it ideal for processing Vietnamese voice recordings.

How do I generate a TOML transcript with precise word timing from a voice file?

To generate a TOML transcript with precise word timing, provide your source audio file to the Skill. It processes the audio using Whisper and outputs detailed timing information for each word and sentence in TOML format.

Do I need to install pyparsing to generate word timestamps from audio?

Yes, you need pyparsing installed to generate word timestamps from audio. While faster-whisper or OpenAI Whisper handles the audio transcription, pyparsing is explicitly required for the TOML generation process.

Can OpenAI Whisper be used for semantic asset mapping through audio transcription?

Yes, OpenAI Whisper can be used for semantic asset mapping through audio transcription. This Skill extracts accurate word-level timing from audio, providing the precise transcript timing necessary to map semantic assets effectively.