whisper

Transcribe multilingual audio and detect languages using Whisper models.

Updated May 1, 2026
One-click install
npx skills add https://github.com/xiaoquqi/hermes-agent-skills --skill whisper-xiaoquqi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: whisper
Source: https://github.com/xiaoquqi/hermes-agent-skills/tree/main/mlops/models/whisper
Command: npx skills add https://github.com/xiaoquqi/hermes-agent-skills --skill whisper-xiaoquqi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Whisper eliminates the manual effort of transcribing audio and identifying language, enabling automated, multilingual transcription and translation workflows.

Core Features & Use Cases

  • Multilingual transcription: supports 99 languages with language identification.
  • Translation: translate non-English audio to English for downstream analysis.
  • Flexible deployment: from tiny to large models, with recommendations for accuracy vs speed in podcast, meeting, and video workflows.

Quick Start

Transcribe an audio file with Whisper using the base model to generate a plain-text transcript.

Frequently Asked Questions about whisper

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

FAQPage Schema
How do I automate multilingual speech recognition for podcast audio?▼

Automating multilingual speech recognition processes podcast audio by identifying the spoken language and generating a text transcription. It supports 99 languages and offers model options from tiny to large to balance accuracy and speed.

Can I translate non-English audio to English text automatically?▼

Translating non-English audio to English text automatically converts spoken foreign language segments into English. This translation workflow enables downstream text analysis directly from the original audio or video recordings.

How do I transcribe an audio file using the Whisper base model?▼

Transcribing an audio file with the base model executes speech-to-text processing to output a plain-text transcript. You specify the base model to achieve a baseline balance of processing speed and accuracy.

Which model size should I use for meeting transcription versus video workflows?▼

Model size for meeting transcription versus video workflows depends on your accuracy and speed requirements. Tiny models offer faster processing, while large models provide higher accuracy for complex multilingual audio.

Do I need Python tooling to run automated speech-to-text transcription?▼

Automated speech-to-text transcription requires Python tooling dependencies to execute the processing logic. Specifying these dependencies ensures the environment is correctly configured for multilingual language detection and transcription tasks.

What is the best way to process multilingual audio with automatic language detection?▼

Processing multilingual audio with automatic language detection identifies the spoken language before applying speech recognition. This approach handles 99 languages, ensuring accurate transcription across podcasts, meetings, and videos.