Local Whisper

Local speech-to-text using OpenAI Whisper. Runs fully offline after model download. High quality transcription with multiple model sizes.

araa47

@araa47

What This Skill Does

Transcribes audio files to text using OpenAI Whisper models, running entirely offline after the initial model download. Supports multiple model sizes from tiny to large-v3, with options for timestamps, JSON output, and language selection.

Replaces cloud-based transcription services by providing high-quality, private, offline speech-to-text with no data leaving your machine.

When to Use It

  • Transcribe meeting recordings or lecture audio to searchable text
  • Generate subtitles or captions for video content with word-level timestamps
  • Convert voice memos or dictation notes into written documents
  • Process sensitive audio files that cannot be sent to cloud services
  • Batch transcribe multiple audio files for archival or analysis

Install

$ openclaw skills install @araa47/local-whisper

Local Whisper STT

Local speech-to-text using OpenAI's Whisper. Fully offline after initial model download.

Usage

# Basic
~/.clawdbot/skills/local-whisper/scripts/local-whisper audio.wav

# Better model
~/.clawdbot/skills/local-whisper/scripts/local-whisper audio.wav --model turbo

# With timestamps
~/.clawdbot/skills/local-whisper/scripts/local-whisper audio.wav --timestamps --json

Models

ModelSizeNotes
tiny39MFastest
base74MDefault
small244MGood balance
turbo809MBest speed/quality
large-v31.5GBMaximum accuracy

Options

  • --model/-m — Model size (default: base)
  • --language/-l — Language code (auto-detect if omitted)
  • --timestamps/-t — Include word timestamps
  • --json/-j — JSON output
  • --quiet/-q — Suppress progress

Setup

Uses uv-managed venv at .venv/. To reinstall:

cd ~/.clawdbot/skills/local-whisper
uv venv .venv --python 3.12
uv pip install --python .venv/bin/python click openai-whisper torch --index-url https://download.pytorch.org/whl/cpu

Top skills in this category