据 AlphaMoat 统计,截至 2026-09,Parakeet Stt 累计下载 3,395 次、获 1 个星标,在全部 5,078 个 AI 技能中排名第 3,299 位,在「设计创意」分类(512 个)中排名第 304 位。

累计安装

185

累计下载

3,395

星标

全站排名

#3,299

全站前 65% · 「设计创意」前 60%

平台	累计安装	累计下载	星标	评论
ClawHub ↗	107	3,209	1	2
SkillHub ↗	185	3,395	1	—

各平台的计数口径不同,统计时间不一致。

这个技能是做什么的

主文介绍基于 ONNX Runtime 的 CPU 本地转写，并提供兼容 OpenAI 的 API 和文本、JSON、带时间戳分段、SRT、VTT 等输出格式。主文声明速度约为 Whisper 的 30x，并支持 25 种语言；这些是来源中的产品说明，实际效果取决于部署环境。

资料发布于 2026-10-27

可以用来做什么

将本地音频文件转写为文本
生成带时间戳的分段或字幕文件

什么时候用

希望在本地服务中处理语音录音时
需要文本、时间戳或字幕等转写输出时

示例提示词

以下是根据技能文档生成的示例,不代表实际运行结果。

把这段本地录音转写成文本，并保留可用的时间戳

说明如何通过本地兼容 API 生成 SRT 字幕

月度数据趋势

累计下载3,395

星标1

2026-09 起统计方法调整:同名技能按作者分别统计,并覆盖全部技能。图中虚线为调整前的月份,与之后的数据不直接比较,也不计算跨越调整的增长。

月份	累计下载	环比	星标
2026-09	3,395	—	1
2026-08	3,167	+3.9%	1
2026-07	3,048	+6.8%	1
2026-06	2,854	+4.0%	1
2026-05	2,744	—	1
2026-03	2,345	—	1

SKILL.md 原文

以下是作者发布的原始文件,按纯文本显示,本站未做修改或审核;其中的链接不可点击,命令请核实后再运行。抓取于 2026-10-23。

3.0 KB · ClawHub v1.1.0

---
name: parakeet-stt
description: >-
  Local speech-to-text with NVIDIA Parakeet TDT 0.6B v3 (ONNX on CPU).
  30x faster than Whisper, 25 languages, auto-detection, OpenAI-compatible API.
  Use when transcribing audio files, converting speech to text, or processing
  voice recordings locally without cloud APIs.
homepage: https://github.com/groxaxo/parakeet-tdt-0.6b-v3-fastapi-openai
metadata: {"clawdbot":{"emoji":"🦜","env":["PARAKEET_URL"]}}
---

展开全部(共 122 行)


# Parakeet TDT (Speech-to-Text)

Local transcription using NVIDIA Parakeet TDT 0.6B v3 with ONNX Runtime.
Runs on CPU — no GPU required. ~30x faster than realtime.

## Installation

```bash
# Clone the repo
git clone https://github.com/groxaxo/parakeet-tdt-0.6b-v3-fastapi-openai.git
cd parakeet-tdt-0.6b-v3-fastapi-openai

# Run with Docker (recommended)
docker compose up -d parakeet-cpu

# Or run directly with Python
pip install -r requirements.txt
uvicorn app.main:app --host 0.0.0.0 --port 5000
```

Default port is `5000`. Set `PARAKEET_URL` to override (e.g., `http://localhost:5092`).

## API Endpoint

OpenAI-compatible API at `$PARAKEET_URL` (default: `http://localhost:5000`).

## Quick Start

```bash
# Transcribe audio file (plain text)
curl -X POST $PARAKEET_URL/v1/audio/transcriptions \
  -F "file=@/path/to/audio.mp3" \
  -F "response_format=text"

# Get timestamps and segments
curl -X POST $PARAKEET_URL/v1/audio/transcriptions \
  -F "file=@/path/to/audio.mp3" \
  -F "response_format=verbose_json"

# Generate subtitles (SRT)
curl -X POST $PARAKEET_URL/v1/audio/transcriptions \
  -F "file=@/path/to/audio.mp3" \
  -F "response_format=srt"
```

## Python / OpenAI SDK

```python
import os
from openai import OpenAI

client = OpenAI(
    base_url=os.getenv("PARAKEET_URL", "http://localhost:5000") + "/v1",
    api_key="not-needed"
)

with open("audio.mp3", "rb") as f:
    transcript = client.audio.transcriptions.create(
        model="parakeet-tdt-0.6b-v3",
        file=f,
        response_format="text"
    )
print(transcript)
```

## Response Formats

| Format | Output |
|--------|--------|
| `text` | Plain text |
| `json` | `{"text": "..."}` |
| `verbose_json` | Segments with timestamps and words |
| `srt` | SRT subtitles |
| `vtt` | WebVTT subtitles |

## Supported Languages (25)

English, Spanish, French, German, Italian, Portuguese, Polish, Russian,
Ukrainian, Dutch, Swedish, Danish, Finnish, Norwegian, Greek, Czech,
Romanian, Hungarian, Bulgarian, Slovak, Croatian, Lithuanian, Latvian,
Estonian, Slovenian

Language is auto-detected — no configuration needed.

## Web Interface

Open `$PARAKEET_URL` in a browser for drag-and-drop transcription UI.

## Docker Management

```bash
# Check status
docker ps --filter "name=parakeet"

# View logs
docker logs -f <container-name>

# Restart
docker compose restart

# Stop
docker compose down
```

## Why Parakeet over Whisper?

- **Speed**: ~30x faster than realtime on CPU
- **Accuracy**: Comparable to Whisper large-v3
- **Privacy**: Runs 100% locally, no cloud calls
- **Compatibility**: Drop-in replacement for OpenAI's transcription API