Speech To Text
This skill implements speech-to-text using Faster Whisper for converting audio input into written transcriptions. It prioritizes local processing, immediate deletion of audio data, and secure handling of voice information while supporting real-time streaming, multiple languages, and hardware-optimized model selection.
Speech To Text converts spoken audio into written text using Faster Whisper with privacy-first local processing.
AI-generated summary based on this skill's SKILL.md
Install
martinholovsky/claude-skills-generator/speech-to-text · repository language: Shell
git clone https://github.com/martinholovsky/claude-skills-generator
cp -r claude-skills-generator ~/.claude/skills/speech-to-textgenerated, unverified - the skill's exact subdirectory could not be determined; check the repository on GitHub
npx skillfed install martinholovsky/claude-skills-generator/speech-to-textFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What does Speech To Text do?
Speech To Text is a skill that converts spoken audio or voice recordings into written text using Faster Whisper technology. It handles real-time streaming, supports multiple languages, and processes audio locally with immediate deletion of voice data for privacy and security.
How do I convert audio to text with this skill?
Speech To Text accepts audio input and transcribes it into written text. The skill processes your audio locally on your device, ensuring immediate deletion of voice data after transcription. It supports various audio formats and can handle both pre-recorded files and real-time streaming.
Can Speech To Text transcribe speech for accessibility?
Yes, Speech To Text transcribes speech for accessibility and documentation purposes. By converting spoken words to text, it enables voice-based input workflows and creates written records of audio content, making information accessible in text form for users who need it.
What audio transcription tool features does Speech To Text offer?
Speech To Text provides hardware-optimized model selection, real-time streaming capabilities, and multi-language support. The skill prioritizes secure handling by processing audio locally and deleting voice information immediately after transcription, ensuring your data remains private.
How does Speech To Text handle my voice data?
Speech To Text processes all audio locally on your device rather than sending it to external servers. Voice data is deleted immediately after transcription completes, ensuring maximum privacy and security. The skill never stores or retains your audio recordings.
What license does Speech To Text use?
Speech To Text is released under the Unlicense, which places it in the public domain. This means you have complete freedom to use, modify, and distribute the skill without restrictions or attribution requirements.