Transcribe and translate audio across 99 languages using OpenAI Whisper.
npx skills add https://github.com/heysuhas/hermes_cli --skill whisper-heysuhas
Please help me install this Agent Skill. Skill: whisper Source: https://github.com/heysuhas/hermes_cli/tree/main/optional-skills/mlops/whisper Command: npx skills add https://github.com/heysuhas/hermes_cli --skill whisper-heysuhas
This skill solves the challenge of converting spoken audio into accurate, timestamped text across 99 different languages, eliminating the need for manual transcription or expensive cloud-based services.
Use the whisper skill to transcribe the audio file named meeting_recording.mp3 and save the output as a text file.
High-intent search queries and answers about installing and using this skill.
Audio transcription to text using the Whisper model runs locally via the openai-whisper, transformers, and torch libraries, executing inference directly on CPU or GPU hardware without cloud services. It supports podcast, meeting, and subtitle generation tasks.
Whisper can automatically detect languages and translate non-English audio directly into English text. It performs high-accuracy speech-to-text transcription and translation across 99 languages natively.
A GPU is not required to run speech-to-text transcription with Whisper. The model supports local inference on either CPU or GPU hardware, provided the openai-whisper, transformers, and torch dependencies are installed.
The best way to generate multilingual subtitles without cloud services is running local Whisper inference. It converts spoken audio into accurate, timestamped text across 99 languages, eliminating expensive cloud transcription dependencies.
The Whisper speech-to-text model supports transcription and translation across 99 languages. It automatically identifies the spoken language and processes diverse audio tasks including podcast documentation and meeting minutes.
Yangel-hideTranscribe and translate multilingual audio into text using OpenAI Whisper.
hmzainjamilConvert audio and video recordings into transcripts, subtitles, and meeting notes.
zeronx798Transcribe multilingual audio files into text using OpenAI's Whisper model.
JiayueMeng128Transcribe and translate audio files locally using the Whisper CLI.
