Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add malue-ai/dazee-small --skill mlx-whispergit clone --depth 1 https://github.com/malue-ai/dazee-smallWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/malue-ai/dazee-small/mlx-whisper)<a href="https://agentmods.dev/skills/malue-ai/dazee-small/mlx-whisper"><img src="https://agentmods.dev/badge/skills/malue-ai/dazee-small/mlx-whisper/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/malue-ai/dazee-small/mlx-whisper"><img src="https://agentmods.dev/badge/skills/malue-ai/dazee-small/mlx-whisper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00026 | $0.00571 |
| Opus 5 | $0.00013 | $0.00285 |
| Sonnet 5 | $0.00005 | $0.00114 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
mlx-whisper scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
MLX Whisper 语音转文字
利用 Apple Silicon 的 MLX 框架本地转录语音，速度是 OpenAI Whisper 的 10 倍。完全离线，隐私安全。
使用场景
- 用户说「帮我把这段录音转成文字」「转录这个音频文件」
- 需要快速转录会议录音、语音备忘录
- 优先于 openai-whisper（更快）和 openai-whisper-api（免费、隐私）
前置条件
pip install mlx-whisper
需要 Apple Silicon Mac（M1/M2/M3/M4）。
执行方式
基本转录
import mlx_whisper
result = mlx_whisper.transcribe(
"audio.mp3",
path_or_hf_repo="mlx-community/whisper-large-v3-turbo",
)
print(result["text"])
带时间戳
result = mlx_whisper.transcribe(
"audio.mp3",
path_or_hf_repo="mlx-community/whisper-large-v3-turbo",
word_timestamps=True,
)
for segment in result["segments"]:
print(f"[{segment['start']:.1f}s - {segment['end']:.1f}s] {segment['text']}")
模型选择
| 模型 | 大小 | 速度 | 准确度 |
|---|---|---|---|
whisper-tiny |
39M | 最快 | 一般 |
whisper-base |
74M | 快 | 较好 |
whisper-small |
244M | 中 | 好 |
whisper-large-v3-turbo |
809M | 较慢 | 最佳 |
默认使用 large-v3-turbo，短音频（<1分钟）可用 small 加速。
语言指定
result = mlx_whisper.transcribe("audio.mp3", language="zh")
输出规范
- 默认输出纯文本
- 用户需要时提供带时间戳的分段输出
- 长音频显示转录进度
- 首次使用时自动下载模型（约 800MB），提醒用户
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 81 lines · 26 tokens per session scan A 368c90c0bac2
mlx-whisper is a skill published in the GitHub repository malue-ai/dazee-small (36 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 571 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.