openai-whisper

TotalClaw 作者 totalclaw

使用 Whisper CLI 进行本地语音转文本(无 API 密钥)。

安装 / 下载方式

TotalClaw CLI推荐
totalclaw install totalclaw:totalclaw~mohdalhashemi98-hue-mh-openai-whisper
cURL直接下载,无需登录
curl -fsSL https://skills.taituai.com/api/skills/totalclaw%3Atotalclaw~mohdalhashemi98-hue-mh-openai-whisper/file -o mohdalhashemi98-hue-mh-openai-whisper.md
## 概述(中文)

使用 Whisper CLI 进行本地语音转文本(无 API 密钥)。

## 原文

# Whisper (CLI)

Use `whisper` to transcribe audio locally.

Quick start

- `whisper /path/audio.mp3 --model medium --output_format txt --output_dir .`
- `whisper /path/audio.m4a --task translate --output_format srt`

Notes

- Models download to `~/.cache/whisper` on first run.
- `--model` defaults to `turbo` on this install.
- Use smaller models for speed, larger for accuracy.