By araa47Updated 2026-05-11local-stt@clawhub_araa47/local-stt
Audio
According to AlphaMoat, as of 2026-09, Local STT (Nvidia Parakeet + Whisper Support) has 3,904 downloads and 1 stars — ranked #2,660 of 5,078 AI skills overall, and #248 of 512 in Design & Media.
| Platform | Installs | Downloads | Stars | Comments |
|---|---|---|---|---|
| ClawHub ↗ | 121 | 3.6K | 1 | - |
| SkillHub ↗ | 222 | 3.9K | 1 | — |
Platforms count differently and update at different times.
Local STT with selectable backends - Parakeet (best accuracy) or Whisper (fastest, multilingual).
The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.
| Month | Downloads | MoM | Stars |
|---|---|---|---|
| 2026-09 | 3.9K | — | 1 |
| 2026-08 | 3.6K | +3.9% | 1 |
| 2026-07 | 3.4K | +6.9% | 1 |
| 2026-06 | 3.2K | +3.9% | 1 |
| 2026-05 | 3.1K | — | 1 |
| 2026-03 | 2.6K | — | 1 |
The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.
---
name: local-stt
description: Local STT with selectable backends - Parakeet (best accuracy) or Whisper (fastest, multilingual).
metadata: {"openclaw":{"emoji":"🎙️","requires":{"bins":["ffmpeg"]}}}
---
# Local STT (Parakeet / Whisper)
Unified local speech-to-text using ONNX Runtime with int8 quantization. Choose your backend:
- **Parakeet** (default): Best accuracy for English, correctly captures names and filler words
- **Whisper**: Fastest inference, supports 99 languages
## Usage
```bash
# Default: Parakeet v2 (best English accuracy)
~/.openclaw/skills/local-stt/scripts/local-stt.py audio.ogg
# Explicit backend selection
~/.openclaw/skills/local-stt/scripts/local-stt.py audio.ogg -b whisper
~/.openclaw/skills/local-stt/scripts/local-stt.py audio.ogg -b parakeet -m v3
# Quiet mode (suppress progress)
~/.openclaw/skills/local-stt/scripts/local-stt.py audio.ogg --quiet
```
## Options
- `-b/--backend`: `parakeet` (default), `whisper`
- `-m/--model`: Model variant (see below)
- `--no-int8`: Disable int8 quantization
- `-q/--quiet`: Suppress progress
- `--room-id`: Matrix room ID for direct message
## Models
### Parakeet (default backend)
| Model | Description |
|-------|-------------|
| **v2** (default) | English only, best accuracy |
| v3 | Multilingual |
### Whisper
| Model | Description |
|-------|-------------|
| tiny | Fastest, lower accuracy |
| **base** (default) | Good balance |
| small | Better accuracy |
| large-v3-turbo | Best quality, slower |
## Benchmark (24s audio)
| Backend/Model | Time | RTF | Notes |
|---------------|------|-----|-------|
| Whisper Base int8 | 0.43s | 0.018x | Fastest |
| **Parakeet v2 int8** | 0.60s | 0.025x | Best accuracy |
| Parakeet v3 int8 | 0.63s | 0.026x | Multilingual |
## openclaw.json
```json
{
"tools": {
"media": {
"audio": {
"enabled": true,
"models": [
{
"type": "cli",
"command": "~/.openclaw/skills/local-stt/scripts/local-stt.py",
"args": ["--quiet", "{{MediaPath}}"],
"timeoutSeconds": 30
}
]
}
}
}
}
```
以 JSON 或薄 HTML 稳定生成泳道、层级卡片和共享轨道矩阵，支持交互式结构图及原生可编辑 PPTX、Visio 导出
Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.
Local speech-to-text with the Whisper CLI (no API key).
Generate and edit diagrams with the mcp-diagram-generator MCP server. Use this skill for new diagrams, existing .drawio/.mmd/.excalidraw edits, network topology, architecture, flowchart, swimlane, sequence, class, ER, and Excalidraw whiteboard work. Always use this skill when the user asks to draw,
Design intelligence and implementation guidance for polished interfaces, from layout and flows to tokens and frontend changes.
Create AI videos with Sora 2, Veo 3, Seedance, Runway, and modern APIs using reliable prompt and rendering workflows.
Pull a frame out of a video with ffmpeg, or produce a thumbnail for a quick look.
Turn audio files into text with local Whisper, running fully offline once the model is downloaded.
Data month: 2026-09 · Downloads, stars and installs are aggregated monthly from public skill registries (ClawHub, SkillHub). See methodology.