What makes STT Recognizer | STT 识别器 notable?

997 downloads. Trust evidence available

How should STT Recognizer | STT 识别器 be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

STT Recognizer | STT 识别器

语音转文字（Speech-to-Text / STT）工具。支持从麦克风录音，使用 Whisper（faster-whisper）在本地进行语音转文字，或通过 OpenAI 兼容 API 进行云端转写。触发词：录音、语音转文字、STT、语音识别、转写、录音转文字。适用平台：Linux / Windows... Skill: STT Recognizer | STT 识别器 Owner: moroiser Summary: 语音转文字（Speech-to-Text / STT）工具。支持从麦克风录音，使用 Whisper（faster-whisper）在本地进行语音转文字，或通过 OpenAI 兼容 API 进行云端转写。触发词：录音、语音转文字、STT、语音识别、转写、录音转文字。适用平台：Linux / Windows... Tags: latest:1.0.8 Version history: v1.0.8 | 2026-04-29T14:09:00.715Z | user 1. Fix all internal path references and display names to match the renamed stt-recognizer slug. 修复所有内部路径引用和展示名，统一为新命名的 stt-rec

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

997

Updated

Oct 11, 2026

Version

1.0.8

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 997 downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 997 downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.8release · observed Apr 29, 2026
Handshake status: UNKNOWNsecurity

What changed

Newest first. Only changes that point at a source are listed.

Release 1.0.8release
1. Fix all internal path references and display names to match the renamed stt-recognizer slug. 修复所有内部路径引用和展示名，统一为新命名的 stt-recognizer。
Observed Apr 29, 2026 · source

Install and run

Setup complexity: medium.

clawhub skill install s1708w2t7w31qf7b0gsy7kamnx83gqa6:stt-recognizer

Python environment detected. Create a strict virtual environment (`python -m venv .venv`) before installing dependencies to prevent system-level package conflicts.
Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
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-moroiser-stt-recognizer/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

92,832 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: STT Recognizer | STT 识别器
description: |
  语音转文字（Speech-to-Text / STT）工具。
  支持从麦克风录音，使用 Whisper（faster-whisper）在本地进行语音转文字，
  或通过 OpenAI 兼容 API 进行云端转写。
  触发词：录音、语音转文字、STT、语音识别、转写、录音转文字。
  适用平台：Linux / Windows / macOS。
---

# STT Recognizer | STT 识别器 🎤

将语音转换为文字，支持本地推理和 API 调用。

---

## 文件结构

```
技能目录（发布用）：
~/.openclaw/workspace/skills/stt-recognizer/
├── SKILL.md           # 本文档
├── _meta.json         # 元数据
├── .clawhub/          # ClawHub 源信息
└── scripts/           # 运行时脚本
    ├── download_models.sh      # 下载模型
    ├── record_audio.py         # 录音
    ├── transcribe.py          # 转写
    └── record_and_transcribe.py # 一键录音+转写

项目目录（运行时数据）：
~/.openclaw/workspace/projects/stt-recognizer/
├── requirements.txt   # Python 依赖
├── recordings/       # 录音文件
└── transcriptions/   # 转写结果

模型缓存（统一命名，技能专属）：
~/.cache/huggingface/modules/stt-recognizer/
├── small/        # small 模型（464MB，默认使用）
└── base/        # base 模型（约 142MB，可选）
```

---

## 目录

1. [概述](#概述)
2. [快速开始](#快速开始)
3. [录音脚本](#录音脚本)
4. [转写脚本](#转写脚本)
5. [模型管理](#模型管理)
6. [输出目录](#输出目录)
7. [环境变量](#环境变量)
8. [故障排查](#故障排查)

---

## 概述

### 支持的转写引擎

| 引擎 | 说明 | 优点 |
|------|------|------|
| `faster-whisper` | 本地 GPU/CPU 高效推理 | 快速、免费、无需网络 |
| `whisper` | OpenAI 原生 Whisper | 准确、完整功能 |
| `api` | OpenAI 兼容 API | 可用云端算力、支持大模型 |

### 支持的音频格式

- WAV (推荐，16-bit PCM)
- MP3
- OGG
- FLAC
- M4A

---

## 快速开始

### 1. 安装依赖

```bash
cd ~/.openclaw/workspace/skills/stt-recognizer
pip install -r requirements.txt --break-system-packages
```

### 2. 下载模型

```bash
cd ~/.openclaw/workspace/skills/stt-recognizer
bash scripts/download_models.sh base
```

### 3. 录音并转写

```bash
# 方式一：一键录音+转写（推荐）
python3 scripts/record_and_transcribe.py --duration 10

# 方式二：分开执行
# 录制 10 秒音频
python3 scripts/record_audio.py --duration 10

# 转写音频文件
python3 scripts/transcribe.py ~/.openclaw/workspace/projects/stt-recognizer/recordings/recording_xxx.wav
```

---

## 录音脚本

### record_and_transcribe.py ⭐ 推荐

一键录音并转写，适合快速使用：

```bash
cd ~/.openclaw/workspace/skills/stt-recognizer
python3 scripts/record_and_transcribe.py --duration 10 --language zh
```

| 参数 | 默认值 | 说明 |
|------|--------|------|
| `--duration` | 10 | 录音时长（秒） |
| `--language` | (自动) | 语言代码，留空自动检测 |
| `--model` | base | 模型大小 |
| `--engine` | faster-whisper | 转写引擎 |

### record_audio.py

从麦克风录制音频，输出 WAV 文件。

```bash
cd ~/.openclaw/workspace/skills/stt-recognizer
python3 scripts/record_audio.py \
    --duration 10 \
    --sample-rate 16000 \
    --channels 1
```

**参数说明**:

| 参数 | 默认值 | 说明 |
|------|--------|------|
| `--duration` | 10 | 录音时长（秒） |
| `--sample-rate` | 16000 | 采样率（Hz），Whisper 推荐 16000 |
| `--channels` | 1 | 声道数，1=单声道 |
| `--list-devices` | - | 列出可用的音频设备 |
| `--output-dir` | projects/stt-recognizer/recordings | 输出目录 |
| `--filename` | auto | 输出文件名 |

**示例**:

```bash
# 列出所有音频设备
python3 scripts/record_audio.py --list-devices

# 录制 30 秒
python3 scripts/record_audio.py --duration 30 --filename my_voice.wav
```

---

## 转写脚本

### transcribe.py

将音频文件转写为文字。

```bash
cd ~/.openc

_meta.json

{
  "ownerId": "kn75k53tcdhqwka2fra5x817p9821zpb",
  "slug": "stt-recognizer",
  "version": "1.0.8",
  "publishedAt": 1777471740715
}

skill-card.md

## Description:

Speech-to-text skill that records microphone audio and transcribes audio files locally with Whisper/faster-whisper or through an OpenAI-compatible API.

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

## Publisher:

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

### License/Terms of Use:

MIT-0

## Use Case:

Developers and end users can record speech or submit audio files for transcription, choosing local Whisper inference or an OpenAI-compatible API based on privacy, hardware, and connectivity needs.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill can record microphone audio and upload audio to an OpenAI-compatible API, which may expose sensitive speech.

Mitigation: Get explicit user consent, prefer local transcription for sensitive audio, use only trusted HTTPS endpoints or intentional localhost endpoints, and delete recordings and transcripts when no longer needed.

Risk: Dependency installation guidance uses broad version ranges and includes --break-system-packages.

Mitigation: Install in a virtual environment and pin or lock dependencies before operational use.

Risk: API keys can be passed through command-line options and may be exposed through shell history or process listings.

Mitigation: Avoid passing API keys on the command line; use a secret manager or protected environment configuration and rotate keys if exposure is suspected.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/moroiser/skills/stt-recognizer)

## Skill Output:

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

**Output Format:** [Markdown guidance with bash commands; runtime outputs include WAV recordings and text transcription files.]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Transcriptions may be saved as txt, srt, or vtt files; recorded audio and transcripts can remain on disk until deleted.]

## Skill Version(s):

1.0.8 (source: server release metadata and artifact _meta.json)

## 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.

requirements.txt

# Audio STT Skill - Python Dependencies
# Install: pip install -r requirements.txt

# ── Core STT Engines ────────────────────────────────────────────────────────
# Option 1: faster-whisper (recommended - GPU/CPU efficient)
faster-whisper>=1.0.0

# Option 2: openai-whisper (full model, slower but accurate)
# Note: Install ONLY one of faster-whisper or whisper, not both
# whisper>=20231117

# ── Audio Recording ─────────────────────────────────────────────────────────
# Option 1: PyAudio (cross-platform)
pyaudio>=0.2.14

# Option 2: SoundDevice + SoundFile (alternative)
# sounddevice>=0.4.5
# soundfile>=0.12.1

# ── API Support ────────────────────────────────────────────────────────────
# For OpenAI-compatible API transcription
openai>=1.0.0

# ── Core ───────────────────────────────────────────────────────────────────
numpy>=1.24.0
torch>=2.0.0

# ── Platform-specific ──────────────────────────────────────────────────────
# Linux: for ALSA audio recording
# alsaaudio (optional, for arecord fallback)

# macOS: for AVFoundation (included in system)

Github ReposUpdated 3d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular