Xpersona
L

Local Whisper

CLAWHUB · Unverified

Local speech-to-text using OpenAI Whisper. Runs fully offline after model download. High quality transcription with multiple model sizes. Skill: Local Whisper Owner: araa47 Summary: Local speech-to-text using OpenAI Whisper. Runs fully offline after model download. High quality transcription with multiple model sizes. Tags: latest:1.0.0 Version history: v1.0.0 | 2026-01-23T09:18:54.671Z | auto - Initial release of local-whisper: local speech-to-text using OpenAI Whisper, fully offline after model download. - Supports multiple model sizes for different

62
Rank
84
Safety
14k
Downloads

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 14.2K downloads reported by the source. Last updated 11/16/2026.

Avoid when

  • Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Install and run

Setup complexity: low.

clawhub skill install s17ba5f8fxv5hp99aaj44pk04h885zwf:local-whisper
  1. Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
  2. Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-araa47-local-whisper--whisper-2/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

4,350 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: local-whisper
description: Local speech-to-text using OpenAI Whisper. Runs fully offline after model download. High quality transcription with multiple model sizes.
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
```

_meta.json

{
  "ownerId": "kn74rm3nhtpv387m12frad6bws7z5kqr",
  "slug": "local-whisper",
  "version": "1.0.0",
  "publishedAt": 1769159934671
}

skill-card.md

## Description:

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

This skill is ready for commercial/non-commercial use.

## Publisher:

[araa47](https://clawhub.ai/user/araa47)

### License/Terms of Use:


## Use Case:

Developers and agents use this skill to transcribe local audio files with OpenAI Whisper, choosing model size, language, timestamp, JSON, and quiet-mode options.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Initial dependency and model downloads can be large and may vary over time.

Mitigation: Install as an unprivileged user and pin or review package versions when reproducible or tightly controlled installs are required.

Risk: Audio inputs and generated transcripts may contain sensitive spoken content.

Mitigation: Process only authorized local audio files and review transcripts before sharing or storing them outside the local environment.

## Reference(s):

- [Local Whisper ClawHub release](https://clawhub.ai/araa47/skills/local-whisper)
- [PyTorch CPU wheel index](https://download.pytorch.org/whl/cpu)

## Skill Output:

**Output Type(s):** [Text, JSON, Shell commands, Guidance]

**Output Format:** [Plain text transcript or JSON with optional language and segment timestamps; setup and usage guidance may include shell commands.]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Runs locally after the initial Whisper model download; supports model, language, timestamps, JSON, and quiet-mode options.]

## Skill Version(s):

1.0.0 (source: server release metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Sponsored

Ads related to Local Whisper and adjacent AI workflows.