Whisper Transcribe Pi — Development skill for Claude Code
Speech-to-text application for Raspberry Pi using OpenAI Whisper.
How to install Whisper Transcribe Pi
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open sethshoultes/whisper-transcribe-pi and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Whisper Transcribe Pi does
Speech-to-text application for Raspberry Pi using OpenAI Whisper.
Alternatives in Development
- Gmail Sync — /gmail-sync - Sync Application Status from Gmail 36.6k ★
- Speech — Generate spoken audio from text using OpenAI's API with built-in voices 14.6k ★
- Dive — Dive is an open-source MCP Host Desktop Application that seamlessly integrates with any LLMs supporting functi 1.8k ★
README
Whisper Transcribe Pi
A professional speech-to-text application for Raspberry Pi using OpenAI's Whisper model. Available in both Standard and Pro versions with advanced features, modern UI, and comprehensive AI integration supporting Local AI, Claude API, and OpenAI API.
Whisper Transcribe Screenshots
Version Comparison
Standard Version (`whisper_transcribe.py`)
- Simple, lightweight GUI with tkinter
- Real-time speech recognition
- Clipboard integration
- USB microphone support
- Basic transcription history
- Keyboard shortcuts (R/Space to record)
Pro Version (`whisper_transcribe_pro.py`) - NEW!
- Modern UI with CustomTkinter framework
- Dark/Light themes with live preview
- Comprehensive settings with 4-tab interface
- Inline microphone testing with waveform visualization
- AI Integration - Local AI, Claude API, OpenAI API support
- Auto-send & Manual AI processing modes
- AI-powered audio enhancement (Hailo integration)
- Noise reduction & Voice Activity Detection
- Export functionality with timestamped files
- Multiple Whisper models (tiny to medium)
- Multi-language support (12 languages)
- Real-time audio visualization
- Customizable window sizes and fonts
- Professional status indicators
- Advanced audio processing
Requirements
Raspberry Pi
- Raspberry Pi 4 or 5 (recommended: 4GB+ RAM)
- Raspberry Pi OS with Desktop
- USB Microphone
- Python 3.7+
- Internet connection (for initial setup)
AI Integration Requirements
For Local AI (Optional)
- Additional RAM: 8GB recommended for larger models
- Storage Space: 0.6-4GB per model
- Dependencies: Auto-installed during setup
- Models: T
Related Skills
OpenAI Whisper Guide
Claude Code skill for automatic speech recognition using optimal Whisper implementation
Doubao Asr
Agent Skill: Transcribe audio files via ByteDance Volcengine Seed-ASR 2.0 (豆包录音文件识别模型2.0). Best-in-class Chine
Audio
Synthesize, transcribe, or transform speech and audio with Modellix.
Brain Transcribe
Transcribe un audio local con Whisper corriendo en tu máquina. Gratis y sin mandar nada a la nube.
Transcribe Summarize
Claude Code / Codex skill for local-first meeting transcription. Runs Whisper on your own machine across macOS
Video Editing Suite
Seven Claude Code / Cowork skills that turn a long recording into finished short-form video: transcribe, find
Related Agents
Voice Engineer
GAIA voice interaction specialist. Use PROACTIVELY for Whisper ASR, Kokoro TTS, the Talk SDK, speech-to-speech
AI Recon
Delegates to this agent when the user wants to map the AI attack surface of an authorized web application befo
After Effects Scripter
Use this agent when writing, debugging, or optimizing After Effects scripts. Covers the full AE object model i
