commit 5cbdcdeb0175211a9dd00ca488063c1e9fe7806b
Author: zlei9 <zlei9@126.com>
Date:   Sun Mar 29 08:22:58 2026 +0800

    Initial commit with translated description

diff --git a/SKILL.md b/SKILL.md
new file mode 100644
index 0000000..a944f61
--- /dev/null
+++ b/SKILL.md
@@ -0,0 +1,49 @@
+---
+name: local-whisper
+description: "使用OpenAI Whisper进行本地语音转文字。模型下载后可完全离线运行。具备多种模型尺寸的高质量转录。"
+metadata: {"clawdbot":{"emoji":"🎙️","requires":{"bins":["ffmpeg"]}}}
+---
+
+# Local Whisper STT
+
+Local speech-to-text using OpenAI's Whisper. **Fully offline** after initial model download.
+
+## Usage
+
+```bash
+# 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
+
+| Model | Size | Notes |
+|-------|------|-------|
+| `tiny` | 39M | Fastest |
+| `base` | 74M | **Default** |
+| `small` | 244M | Good balance |
+| `turbo` | 809M | Best speed/quality |
+| `large-v3` | 1.5GB | Maximum 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:
+```bash
+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
+```
diff --git a/_meta.json b/_meta.json
new file mode 100644
index 0000000..65b4794
--- /dev/null
+++ b/_meta.json
@@ -0,0 +1,6 @@
+{
+  "ownerId": "kn74rm3nhtpv387m12frad6bws7z5kqr",
+  "slug": "local-whisper",
+  "version": "1.0.0",
+  "publishedAt": 1769159934671
+}
\ No newline at end of file
diff --git a/scripts/transcribe.py b/scripts/transcribe.py
new file mode 100644
index 0000000..70debab
--- /dev/null
+++ b/scripts/transcribe.py
@@ -0,0 +1,70 @@
+#!/usr/bin/env python3
+"""Local speech-to-text using OpenAI Whisper (runs offline after model download)."""
+
+import json
+import sys
+import warnings
+
+import click
+
+warnings.filterwarnings("ignore")
+
+MODELS = ["tiny", "tiny.en", "base", "base.en", "small", "small.en",
+          "medium", "medium.en", "large-v3", "turbo"]
+
+
+@click.command()
+@click.argument("audio_file", type=click.Path(exists=True))
+@click.option("-m", "--model", default="base", type=click.Choice(MODELS), help="Whisper model size")
+@click.option("-l", "--language", default=None, help="Language code (auto-detect if omitted)")
+@click.option("-t", "--timestamps", is_flag=True, help="Include word-level timestamps")
+@click.option("-j", "--json", "as_json", is_flag=True, help="Output as JSON")
+@click.option("-q", "--quiet", is_flag=True, help="Suppress progress messages")
+def main(audio_file, model, language, timestamps, as_json, quiet):
+    """Transcribe audio using OpenAI Whisper (local)."""
+    try:
+        import whisper
+    except ImportError:
+        click.echo("Error: openai-whisper not installed", err=True)
+        sys.exit(1)
+
+    if not quiet:
+        click.echo(f"Loading model: {model}...", err=True)
+
+    try:
+        whisper_model = whisper.load_model(model)
+    except Exception as e:
+        click.echo(f"Error loading model: {e}", err=True)
+        sys.exit(1)
+
+    if not quiet:
+        click.echo(f"Transcribing: {audio_file}...", err=True)
+
+    try:
+        result = whisper_model.transcribe(audio_file, language=language,
+                                          word_timestamps=timestamps, verbose=False)
+    except Exception as e:
+        click.echo(f"Error transcribing: {e}", err=True)
+        sys.exit(1)
+
+    text = result["text"].strip()
+
+    if as_json:
+        output = {"text": text, "language": result.get("language", "unknown")}
+        if timestamps and "segments" in result:
+            output["segments"] = [
+                {"start": s["start"], "end": s["end"], "text": s["text"],
+                 **({"words": s["words"]} if "words" in s else {})}
+                for s in result["segments"]
+            ]
+        click.echo(json.dumps(output, indent=2, ensure_ascii=False))
+    else:
+        click.echo(text)
+        if timestamps and "segments" in result:
+            click.echo("\n--- Segments ---", err=True)
+            for seg in result["segments"]:
+                click.echo(f"  [{seg['start']:.2f}s - {seg['end']:.2f}s]: {seg['text']}", err=True)
+
+
+if __name__ == "__main__":
+    main()