whisper

Transcribe spoken audio into timestamped text across 99 languages.

Updated May 9, 2026

Search Tags:#speech recognition #transcription #whisper #audio processing #multilingual #asr

Ready to run

npx skills add https://github.com/pmcdowall/hermes-skills --skill whisper-pmcdowall

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: whisper
Source: https://github.com/pmcdowall/hermes-skills/tree/main/mlops/models/whisper
Command: npx skills add https://github.com/pmcdowall/hermes-skills --skill whisper-pmcdowall

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill solves the challenge of converting speech recordings into accurate text by providing robust multilingual automatic speech recognition for audio content.

Core Features & Use Cases

Speech Transcription: Convert audio and video files into text with support for 99 languages and timestamped segments.
Translation and Language Processing: Translate non-English speech into English and identify spoken languages for multilingual workflows.
Use Case: Transcribe podcasts, meetings, interviews, or technical discussions into searchable text for analysis, documentation, and automation.

Quick Start

Use the whisper skill to transcribe the attached audio file and return the text with timestamps.

Frequently Asked Questions about whisper

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

FAQPage Schema

How do I transcribe multilingual audio files into searchable text?▼

To transcribe multilingual audio into text, you need speech recognition processing that identifies spoken languages and converts audio recordings into timestamped text segments. This handles podcast transcription and meeting documentation by applying automatic speech recognition workflows.

Can I translate non-English speech into English text during transcription?▼

Yes, translating non-English speech into English text during transcription is supported. The speech-to-text process identifies spoken languages and translates the audio content directly into English as part of the multilingual transcription workflow.

Does multilingual speech recognition work for video captioning podcasts?▼

Multilingual speech recognition works for video captioning podcasts by processing audio tracks into timestamped segments. This automatic speech recognition supports 99 languages, making it suitable for transcribing technical discussions and interviews into searchable text.

How do I get timestamped segments for meeting documentation from audio?▼

Getting timestamped segments for meeting documentation requires running speech-to-text model execution on your audio. The transcription process automatically segments spoken audio into text with corresponding timestamps for accurate documentation and analysis.

What are the limitations of automatic speech recognition for audio processing?▼

Limitations of automatic speech recognition for audio processing depend on configurable model sizes and GPU acceleration availability. Processing accuracy can vary across 99 supported languages, and complex audio translation workflows may require specific hardware support.