Transcribe multilingual audio to text and translate it to English.
npx skills add https://github.com/dawsonblock/HERMY --skill whisper-dawsonblock
Please help me install this Agent Skill. Skill: whisper Source: https://github.com/dawsonblock/HERMY/tree/main/hermes-agent-2026.4.23/optional-skills/mlops/whisper Command: npx skills add https://github.com/dawsonblock/HERMY --skill whisper-dawsonblock
Whisper enables accurate transcription and translation of audio across many languages, turning spoken content into searchable, editable text for accessibility, indexing, and content repurposing.
Install the Whisper package and transcribe an audio file to obtain a text transcript.
High-intent search queries and answers about installing and using this skill.
To transcribe multilingual audio to text, use Whisper to automatically identify the spoken language across 99 options and generate a searchable text transcript from your audio file.
Yes, Whisper translates non-English audio into English text. It processes spoken language in 99 supported languages and outputs an English translation alongside the original transcription.
The best way to generate podcast transcripts and video captions is applying multilingual speech recognition. Whisper provides language-aware transcripts for audio content, turning speech into editable text.
Yes, Whisper supports automatic language identification for meetings. It detects the spoken language automatically across 99 languages, providing accurate multilingual speech-to-text transcription.
Model sizes affect speech recognition by balancing speed, memory usage, and accuracy. Whisper offers flexible sizes from tiny to large, allowing you to optimize based on your available hardware.
For multilingual speech recognition with Whisper, you need to install the Whisper package alongside dependencies including openai-whisper, transformers, and torch to process audio files locally.
AshesOfTheUndeadTranscribe base64 encoded audio files into written text using the z-ai-web-dev-sdk.
buda-aiTranscribe audio and video into timestamped TXT, SRT, and JSON transcripts.
Muath2000Develop and deploy NLP systems with text processing pipelines and model fine-tuning.
dioerdenTranscribe local audio files to text using OpenAI Whisper CLI.
