Transcribe and translate spoken audio into text across 99 languages.
npx skills add https://github.com/Rheasilvia/hermes-desktop --skill whisper-rheasilvia
Please help me install this Agent Skill. Skill: whisper Source: https://github.com/Rheasilvia/hermes-desktop/tree/main/optional-skills/mlops/whisper Command: npx skills add https://github.com/Rheasilvia/hermes-desktop --skill whisper-rheasilvia
This skill solves the challenge of converting spoken audio into accurate, timestamped text across 99 different languages, eliminating the need for manual transcription.
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.
To transcribe audio into text, the Whisper skill processes spoken audio files using the openai-whisper library to generate accurate, timestamped text across 99 languages. It requires Python 3.8-3.11 and ffmpeg to perform robust speech recognition.
Yes, Whisper can automatically translate non-English audio directly into English text. The speech-to-text model identifies the spoken language and translates the audio content into English while generating the transcription output.
Yes, ffmpeg is required to use the openai-whisper library for speech-to-text processing. You also need Python 3.8-3.11 and the torch and transformers dependencies installed to run the speech recognition workflow.
The best way to generate subtitles from multilingual content is using Whisper's speech-to-text transcription to convert spoken audio into timestamped text. This supports 99 languages and handles diverse audio processing tasks like subtitle generation.
Multilingual speech-to-text handles meeting documentation by converting recorded meeting audio into accurate text transcriptions. The Whisper model processes the audio file to generate timestamped text, eliminating the need for manual transcription across 99 languages.
icyzhTranscribe and translate audio files into text using OpenAI Whisper.
hmzainjamilConvert audio and video recordings into transcripts, subtitles, and meeting notes.
heysuhasTranscribe and translate audio across 99 languages using OpenAI Whisper.
NITISH-gitbitTranscribe spoken language to text using OpenAI's Whisper model.
