speech-to-text

Transcribe audio files locally with Faster Whisper speech-to-text.

45|4|Updated Nov 25, 2025

Search Tags:#transcription #privacy #speech-to-text #local processing #voice assistant #faster whisper

Ready to run

npx skills add https://github.com/martinholovsky/claude-skills-generator --skill speech-to-text-martinholovsky

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: speech-to-text
Source: https://github.com/martinholovsky/claude-skills-generator/tree/main/skills/speech-to-text
Command: npx skills add https://github.com/martinholovsky/claude-skills-generator --skill speech-to-text-martinholovsky

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires faster-whisper, numpy, soundfile, webrtcvad, pydub, structlog, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enables local, private, and efficient conversion of spoken audio into written text, crucial for voice assistants and real-time transcription needs without relying on cloud services.

Core Features & Use Cases

Local Transcription: Utilizes Faster Whisper for offline speech-to-text processing.
Privacy-Focused: Ensures audio is processed locally and deleted immediately, with no PII logged.
Performance Optimization: Supports various model sizes and quantization for speed and memory efficiency.
Use Case: Integrate this skill into a voice assistant to process user commands securely and quickly, or to transcribe meeting recordings without sending sensitive audio data externally.

Quick Start

Use the speech-to-text skill to transcribe the audio file 'meeting_recording.wav'.

Frequently Asked Questions about speech-to-text

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I transcribe audio to text locally without sending data to the cloud?▼

Local speech-to-text transcription converts audio to text entirely on your machine. This skill uses the Faster Whisper model for offline processing, ensuring audio data remains private and is deleted immediately after transcription.

How do I optimize speech-to-text performance for speed and memory efficiency?▼

Speech-to-text performance optimization involves selecting various model sizes and applying quantization. These techniques reduce memory usage and increase processing speed while maintaining transcription accuracy locally with Faster Whisper.

Does faster whisper support real-time transcription for voice assistants?▼

Faster Whisper supports real-time transcription suitable for voice assistants. It handles audio processing and transcription optimization locally, allowing secure and quick processing of user commands without external network calls.

What Python libraries are required for local speech-to-text processing?▼

Local speech-to-text processing requires faster-whisper, numpy, and soundfile for audio manipulation. Additional dependencies include webrtcvad, pydub, and structlog for voice activity detection, audio conversion, and structured logging.

How is privacy handled during offline speech-to-text transcription?▼

Privacy in offline speech-to-text transcription is handled by processing audio locally and deleting it immediately after transcription. No personally identifiable information is logged, ensuring sensitive meeting recordings or voice commands remain secure.

Can I use faster whisper for transcribing meeting recordings without uploading audio files?▼

Faster Whisper can transcribe meeting recordings locally without uploading audio files. It processes wav files and other audio formats directly on your hardware, providing a private alternative to cloud-based transcription services.