Transcribe audio into text across 99 languages and translate to English.
npx skills add https://github.com/nadicodeai/argo-agent --skill whisper-nadicodeai
Please help me install this Agent Skill. Skill: whisper Source: https://github.com/nadicodeai/argo-agent/tree/main/optional-skills/mlops/whisper Command: npx skills add https://github.com/nadicodeai/argo-agent --skill whisper-nadicodeai
Whisper enables robust transcription of audio across many languages, enabling developers to turn speech into text and translate when needed, reducing manual transcription work.
Transcribe an audio file by loading an appropriate Whisper model and calling transcribe.
High-intent search queries and answers about installing and using this skill.
To transcribe audio into text, you load a Whisper model, specify the audio language, and call the transcribe function to convert speech into text across 99 supported languages.
Yes, Whisper speech recognition supports translation to English. When requested, it transcribes non-English audio and translates the resulting text directly into English.
Multilingual speech recognition offers multiple Whisper model sizes ranging from tiny to large, plus a turbo option, allowing developers to balance processing speed and transcription accuracy.
Yes, you can use speech-to-text models for podcast transcription, meeting minutes, video captions, and multilingual audio workflows to reduce manual transcription work.
Yes, audio processing with Whisper requires language specification to accurately transcribe speech into text. This ensures the model applies the correct language context during transcription.
math-incTranscribe audio into text using Whisper multilingual speech recognition models.
JamesFincherTranscribe spoken audio into text with optional English translation and timestamps.
dingdyanTranscribes audio files into text using OpenAI's Whisper API.
hochoa13Transcribe audio from 99 languages and translate it to English.
