Transcribe spoken audio into text with timestamps using Whisper.
npx skills add https://github.com/Gitnapp/Skills --skill whisper-gitnapp
Please help me install this Agent Skill. Skill: whisper Source: https://github.com/Gitnapp/Skills/tree/main/mlops/models/whisper Command: npx skills add https://github.com/Gitnapp/Skills --skill whisper-gitnapp
## What problem does it solve? This Skill solves the challenge of converting spoken audio into accurate text across many languages, reducing manual transcription effort and enabling scalable audio understanding workflows.
## Core Features & Use Cases
### Quick Start Use the whisper skill to transcribe the attached audio file and return the text with timestamps.
High-intent search queries and answers about installing and using this skill.
To transcribe multilingual audio into text with timestamps, load a Whisper model, configure transcription parameters, and apply audio preprocessing to generate searchable machine-readable transcripts from podcasts, meetings, or lectures.
Generating video subtitles from spoken audio requires multilingual speech recognition processing. By loading a Whisper model and applying audio preprocessing, you can convert spoken language tracks into timestamped text suitable for subtitle generation workflows.
You can translate non-English speech into English text by applying automatic speech recognition and language identification. The Whisper model processes the audio input, identifies the spoken language, and outputs the translated English text.
Audio transcription works on noisy recordings and interviews by applying audio preprocessing before speech recognition. This handles complex multilingual speech scenarios and converts variable quality audio into searchable, timestamped machine-readable text.
GPU acceleration is optional for automatic speech recognition processing. While the Whisper model can transcribe audio without it, enabling GPU acceleration significantly improves processing efficiency for large-scale audio transcription and translation workflows.
Transcribing long meetings with automatic speech recognition requires loading the Whisper model and applying audio preprocessing to manage resources. Efficient processing of extensive recordings depends on utilizing optional GPU acceleration to handle the computational load effectively.
ericfitzTranslate English text to a target language while preserving placeholders and formatting.
hmzainjamilConvert audio and video recordings into transcripts, subtitles, and meeting notes.
blueskies1818Transcribe speech and identify languages in 99 languages using OpenAI Whisper.
math-incTranscribe audio into text using Whisper multilingual speech recognition models.
