According to AlphaMoat, as of 2026-09, Whisper Transcribe has 4,408 downloads and 5 stars — ranked #2,214 of 5,078 AI skills overall, and #216 of 512 in Design & Media.

Installs

162

Downloads

4.4K

Stars

Overall Rank

#2,214

Top 44% overall · Top 43% in Design & Media

Platform	Installs	Downloads	Stars	Comments
ClawHub ↗	73	2.6K	3	-
SkillHub ↗	162	4.4K	5	—

Platforms count differently and update at different times.

What this skill does

It supports automatic language detection, batch processing, model selection, and text, subtitle, or JSON output. The first run downloads a model. Transcripts may be saved beside the audio or in a chosen directory and can contain sensitive conversation content. For sensitive recordings, use a controlled output directory, limit retention, and review the transcript. Requires the local whisper CLI and ffmpeg. Install reviewed dependencies in a virtual environment and pin them where reproducibility is required. Select a model compatible with available memory and processing time; the model table is guidance rather than a guaranteed accuracy or runtime result.

Profile published 2026-10-27

What you can do with it

Transcribe a meeting, podcast, or voice message
Create subtitles or a transcript with timestamps

When to use it

When audio processing is authorized, dependencies are trusted, and output location and retention are clear

Example prompts

Generated from the skill’s documentation as examples; not results of actual runs.

Explain which transcript formats could be produced for this audio without installing dependencies or processing files.

Choose a controlled output directory for a sensitive recording and list transcript checks before use.

Monthly Trend

Downloads4.4K

Stars5

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	4.4K	—	5
2026-08	3.7K	+16.5%	5
2026-07	3.2K	+12.0%	5
2026-06	2.9K	+7.1%	5
2026-05	2.7K	—	4
2026-03	1.8K	—	2

SKILL.md (original)

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.

1.6 KB · ClawHub v1.0.0

---
name: whisper-transcribe
description: Transcribe audio files to text using OpenAI Whisper. Supports speech-to-text with auto language detection, multiple output formats (txt, srt, vtt, json), batch processing, and model selection (tiny to large). Use when transcribing audio recordings, podcasts, voice messages, lectures, meetings, or any audio/video file to text. Handles mp3, wav, m4a, ogg, flac, webm, opus, aac formats.
---

# Whisper Transcribe

Transcribe audio with `scripts/transcribe.sh`:

```bash

Show all (47 lines)

# Basic (auto-detect language, base model)
scripts/transcribe.sh recording.mp3

# German, small model, SRT subtitles
scripts/transcribe.sh --model small --language de --format srt lecture.wav

# Batch process, all formats
scripts/transcribe.sh --format all --output-dir ./transcripts/ *.mp3

# Word-level timestamps
scripts/transcribe.sh --timestamps interview.m4a
```

## Models

| Model | RAM | Speed | Accuracy | Best for |
|-------|-----|-------|----------|----------|
| tiny | ~1GB | ⚡⚡⚡ | ★★ | Quick drafts, known language |
| base | ~1GB | ⚡⚡ | ★★★ | General use (default) |
| small | ~2GB | ⚡ | ★★★★ | Good accuracy |
| medium | ~5GB | 🐢 | ★★★★★ | High accuracy |
| large | ~10GB | 🐌 | ★★★★★ | Best accuracy (slow on Pi) |

## Output Formats

- **txt** — Plain text transcript
- **srt** — SubRip subtitles (for video)
- **vtt** — WebVTT subtitles
- **json** — Detailed JSON with timestamps and confidence
- **all** — Generate all formats at once

## Requirements

- `whisper` CLI (`pip install openai-whisper`)
- `ffmpeg` (for audio decoding)
- First run downloads the model (~150MB for base)