Transcribe spoken audio into text across 99 languages.
npx skills add https://github.com/graniet/kheish --skill whisper-graniet
Please help me install this Agent Skill. Skill: whisper Source: https://github.com/graniet/kheish/tree/main/skills/mlops/models/whisper Command: npx skills add https://github.com/graniet/kheish --skill whisper-graniet
Manual transcription of audio content is time-consuming, costly, and often fails with multilingual speech, noisy audio, or large volumes of content, making it difficult to turn podcasts, meetings, and interviews into usable, searchable text.
Use the whisper skill to transcribe the attached audio file 'team-standup.mp3' into English text with word-level timestamps.
High-intent search queries and answers about installing and using this skill.
Audio transcription to text in multiple languages is handled by converting spoken audio content into accurate text across 99 supported languages. You can transcribe podcasts, meetings, and interviews, with configurable models to balance speed and accuracy.
Yes, translating non-English speech to English text is supported natively. The skill automatically translates non-English audio recordings into English text, enabling global accessibility for multilingual audio processing and translation tasks.
Yes, you need openai-whisper, transformers, and torch dependencies to run speech-to-text transcription. These libraries power the configurable transcription models that allow adjustable speed, accuracy, and language settings.
Generating meeting notes from recorded calls is done by processing the audio file through the transcription skill. It converts spoken audio content into searchable text, allowing teams to create notes from recorded calls without manual effort.
Yes, podcast transcription with word-level timestamps is supported. The skill transcribes attached audio files into text with configurable settings, allowing content teams to generate subtitles and transcribe dozens of podcast episodes efficiently.
Transcription accuracy for noisy audio or low-resource languages depends on the selected model size. The skill offers multiple model sizes to balance speed and accuracy, but users should configure settings appropriately to handle challenging audio conditions.
519labTranscribe and translate speech to text using OpenAI's Whisper model.
hmzainjamilConvert audio and video recordings into transcripts, subtitles, and meeting notes.
ericfitzTranslate English text to a target language while preserving placeholders and formatting.
steipeteTranscribe local audio files to text or subtitles using the Whisper CLI.
