media-whisper

Transcribe audio or video into SRT/VTT subtitles with word timestamps.

15|4|Updated Apr 18, 2026

Search Tags:#transcription #whisper #multilingual #diarization #faster-whisper #whisper-cpp #subtitle-generation

Ready to run

npx skills add https://github.com/damionrashford/media-os --skill media-whisper

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: media-whisper
Source: https://github.com/damionrashford/media-os/tree/main/skills/media-whisper
Command: npx skills add https://github.com/damionrashford/media-os --skill media-whisper

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires faster-whisper, ctranslate2, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill automates the transcription of audio or video content and the generation of SRT/VTT subtitles, enabling accessible transcripts, captions, and searchable media libraries.

Core Features & Use Cases

Transcription to SRT/VTT with word-level timestamps (via whisper.cpp or faster-whisper).
Translation to English for non-English speech and multilingual support.
Optional speaker diarization to identify speakers in multi-person conversations.

Quick Start

Transcribe input audio or video to SRT, with optional translation to English.

Frequently Asked Questions about media-whisper

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

FAQPage Schema

How do I transcribe audio to SRT subtitles with word-level timestamps?▼

To transcribe audio to SRT subtitles with word-level timestamps, you can use Whisper AI backends like whisper.cpp or faster-whisper, which process podcasts or films and output accurate VTT or SRT caption files.

Can I generate searchable transcripts for multilingual media and translate speech to English?▼

Yes, you can generate searchable transcripts for multilingual media and translate non-English speech to English, allowing you to create accessible captions and searchable libraries from diverse international audio or video sources.

Does faster-whisper support speaker diarization for multi-person interviews?▼

Yes, faster-whisper supports optional speaker diarization for multi-person interviews, allowing the transcription process to identify and separate distinct speakers within conversations, podcasts, and films automatically.

What is the best way to convert video content into SRT or VTT caption files?▼

The best way to convert video content into SRT or VTT caption files is using Whisper AI transcription, which directly processes video inputs to generate accessible subtitles and searchable text transcripts for media libraries.

Do I need ctranslate2 to transcribe podcasts with faster-whisper?▼

Yes, ctranslate2 is a required dependency to transcribe podcasts with faster-whisper, providing the underlying backend engine needed to run the Whisper AI speech recognition and subtitle generation processes efficiently.

When should I use whisper.cpp instead of faster-whisper for transcription?▼

You should choose between whisper.cpp and faster-whisper for transcription based on your environment setup; both serve as backends to generate SRT subtitles and transcripts, with faster-whisper relying on ctranslate2 for processing.