whisper

Transcribe audio to text and generate SRT/VTT subtitles with Whisper.

Updated Apr 3, 2026
One-click install
npx skills add https://github.com/tusosos/manus-knowledge-base --skill whisper-tusosos
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: whisper
Source: https://github.com/tusosos/manus-knowledge-base/tree/main/skills/whisper
Command: npx skills add https://github.com/tusosos/manus-knowledge-base --skill whisper-tusosos

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transcribes audio to text and generates subtitles across local and API-based deployments using Whisper variants, enabling searchable transcripts and accessible media.

Core Features & Use Cases

  • Local and API-based transcription with Whisper (openai-whisper, faster-whisper, whisper.cpp) and the OpenAI Whisper API.
  • Subtitle generation (SRT/VTT/JSON), language detection, translation to English, and word-level timestamps.
  • Speaker diarization and handling multi-speaker recordings for transcripts or meeting notes.
  • Batch processing workflows for podcasts, interviews, meetings, and multimedia archives.

Quick Start

Install a Whisper runtime (e.g., faster-whisper) and transcribe your audio file to generate a transcript and subtitles.

Frequently Asked Questions about whisper

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

FAQPage Schema
How do I transcribe audio to text and generate SRT subtitles using Whisper?

You can transcribe audio to text and generate SRT subtitles using Whisper by deploying local Python runtimes like openai-whisper or faster-whisper, or by connecting to the OpenAI Whisper API.

Can I use faster-whisper for local speech-to-text transcription of podcasts?

Yes, faster-whisper supports local speech-to-text transcription for podcasts, allowing you to process audio archives into searchable text transcripts without relying on external API calls.

Does Whisper support speaker diarization for multi-speaker meeting transcripts?

Yes, Whisper supports speaker diarization for multi-speaker meeting transcripts, applying distinct speaker labels to differentiate participants and clarify conversational attribution within the generated text.

What is the best way to translate audio to English and detect the source language?

The best way to translate audio to English and detect the source language is using Whisper's built-in language detection and translation features, which process spoken audio into translated English text automatically.

Do I need to install Python to use whisper.cpp for audio transcription?

Using whisper.cpp for audio transcription requires a compatible local runtime environment, but it does not strictly require Python like openai-whisper or faster-whisper, offering a lightweight alternative deployment.