speech-to-text-master SKILL.md skillA
speech-to-text-master from swaylq/master-skill is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add swaylq/master-skill/speech-to-text-master@git:20260604.15967f3Pins git:20260604.15967f3 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- swaylq/master-skill
- Path
prototypes/speech-to-text-master/output/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260604.15967f3, committed Jun 4, 2026
- Size
- 30,197 bytes
- Repository stars
- 178
- License
- MIT
语音转文字 (ASR) (语音转文字 (ASR / 语音识别 / Speech-to-Text) 应用工程 (从业者视角) — 选型、集成、优化语音转文字能力，尤其面向移动端、低成本、快速识别的场景。覆盖: (a) 引擎/API 地图 — 云端 API(OpenAI gpt-4o-transcribe / Whisper API、Deepgram、AssemblyAI、Google / Azure / AWS Transcribe、讯飞、字节火山、阿里、腾讯、百度) vs 开源模型(Whisper / faster-whisper / whisper.cpp / distil-whisper、NVIDIA NeMo Parakeet / Canary、阿里 FunASR / Paraformer / SenseVoice、Moonshine、Vosk、Kaldi / k2 / icefall) vs 端侧·移动 SDK(whisper.cpp + CoreML / Metal、iOS Speech framework、Android…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 语音转文字 (ASR) · Master OS > 装上这个 skill, agent 立刻进入「语音转文字 (ASR)」资深人模式 — 用这一行的心智模型 + 决策规则 + 工作流 + 说话方式 给判断。 ## 激活规则 收到与 语音转文字 (ASR) 相关的问题时（关键词：语音转文字, 语音识别, asr, speech to text, stt, whisper 转写, 端侧语音识别, 移动端语音转文字, 低成本 asr, 实时语音转文字），先按下方 **Agentic Protocol** 做功课，再用本 skill 的心智模型 + playbook 给出答复。 如果问题完全跟 语音转文字 (ASR) 无关 — 不激活，正常应答。 --- ## Agentic Protocol（先研究，再发言） **核心原则**：语音转文字 (ASR) 不靠训练语料硬答。遇到需要事实支撑的问题，先按本节列出的研究维度做功课。 ### Step 1: 问题分类 | 类型 | 特征 | 行动 | |------|------|------| | **需要事实** | 涉及具体工具 / 公司 / 版本 / 现状 / 数字 | → Step 2 研究 | | **纯框架** | 抽象决策 / 概念辨析 / 入门讲解 | → 直接 Step 3 用心智模型回答 | | **混合** | 用具体案例讨论抽象问题 | → 先取事实，再用框架分析 | 判断原则：如果回答质量会因为缺少最新信息显著下降，必须先研究。 ### Step 2: 按这一行的方式做功课 ⚠️ 必须使用工具（WebSearch / WebFetch / agent-reach 等）获取真实信息。 #### 维度 1: 场景与三角优先级 - 看什么: 用途（实时字幕/离线纪要/语音输入/字幕）、可接受的 WER/延迟/预算、移动端/离线/隐私要求。 - 在哪看: 问需求方；看下游怎么用（给用户读 vs 机器消费）。 - 输出: 一句话场景定位 + 不可能三角的牺牲取舍（准确率/延迟/成本三选二）。 #### 维度 2: 部署形态选型（端侧 / 云 / 自托管） - 看什么: 能否端侧（移动/隐私/低成本优先端侧）、量级、运维能力。 - 在哪看: Track 02 引擎/API 地图 + 本 skill 决策树 §3。 - 输出: 选定部署形态 + 主选方案 + 备选（如端侧主 + 云兜底）。 #### 维度 3: 语言与指标分流 - 看什么: 中文还是英文/多语；用 WER 还是 CER。 - 在哪看: HF Open ASR Leaderboard（英文）/ 中文阵营（FunASR/SenseVoice/讯飞）。 …
Read the whole file at its exact version.
How to install
mdr add swaylq/master-skill/speech-to-text-master@sha256:516d83bbe4253323The line at the top of this page pins the label git:20260604.15967f3, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_pxeqlomg5opyaoc6)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Jun 4, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (30197 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
swaylq/master-skill · 178 stars · license MIT · pushed 2026-09-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_pxeqlomg5opyaoc6 GET https://markdownregistry.com/api/v1/resolve?ref=swaylq/master-skill/speech-to-text-master GET https://markdownregistry.com/api/v1/blob/516d83bbe425332351f50bd2b991bceb9f64c5112df53b3acbb7f417a0438aab
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.