whisper

Transcribe spoken audio into text with timestamps and optional English translation.

3|Updated Apr 4, 2026

Search Tags:#translation #subtitles #transcription #whisper #multilingual #speech-to-text #audio-processing

Ready to run

npx skills add https://github.com/twjarviszyra-web/hermes-unbound --skill whisper-twjarviszyra-web

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill turns spoken audio into readable text, making recordings searchable, editable, and easier to reuse without manual transcription.

Core Features & Use Cases

Speech-to-Text Transcription: Convert podcasts, meetings, lectures, and interviews into text across many languages.
Translation to English: Translate non-English audio into English for faster review and sharing.
Timestamps and Segments: Generate segment-level and word-level timing for subtitles, captions, and review workflows.
Use Case: If you have a multilingual webinar recording, this Skill can detect the language, transcribe the speech, and produce a timestamped transcript for publishing or analysis.

Quick Start

Ask the skill to transcribe the attached audio file and return a clean transcript 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 an audio recording into text with timestamps?▼

Speech-to-text transcription converts spoken audio from podcasts, meetings, or interviews into readable, searchable text segments with optional timestamped outputs for subtitles and captions.

Can I translate non-English audio recordings directly into English text?▼

Yes, you can translate non-English audio into English by applying language detection or hints to the recording, producing an English transcript for faster sharing and review.

What is the best way to generate subtitles for a multilingual webinar?▼

The best way to generate subtitles for a multilingual webinar is using speech-to-text transcription with language detection to produce timestamped segments formatted for captions.

Does speech-to-text transcription work with podcasts and lectures?▼

Yes, speech-to-text transcription works with podcasts, meetings, lectures, and interviews, converting spoken audio across many languages into searchable, editable transcripts.

How do I handle multilingual audio processing when the spoken language is unknown?▼

Multilingual audio processing handles unknown languages through automatic language detection or by accepting language hints, allowing the transcription model to accurately process recordings.

Do I need to manually select a model for speech-to-text transcription?▼

Yes, this transcription process requires Whisper model selection to define processing parameters, alongside optional language hints or automatic detection for accurate text generation.