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 bleakbelladonnals/asr-transcription-skills --skill speech-to-text-apisgit clone --depth 1 https://github.com/bleakbelladonnals/asr-transcription-skillsWrote 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/bleakbelladonnals/asr-transcription-skills/speech-to-text-apis)<a href="https://agentmods.dev/skills/bleakbelladonnals/asr-transcription-skills/speech-to-text-apis"><img src="https://agentmods.dev/badge/skills/bleakbelladonnals/asr-transcription-skills/speech-to-text-apis/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/bleakbelladonnals/asr-transcription-skills/speech-to-text-apis"><img src="https://agentmods.dev/badge/skills/bleakbelladonnals/asr-transcription-skills/speech-to-text-apis.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 | $0.00090 | $0.01982 |
| Opus 5 | $0.00045 | $0.00991 |
| Sonnet 5 | $0.00018 | $0.00396 |
| Haiku 4.5 | $0.00009 | $0.00198 |
Grade A, and why
speech-to-text-apis scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
6. **查百炼官方文档**：help.aliyun.com 是 SPA，curl 任何 URL 都返回 200 壳页面、无法判断真假 404，必须用浏览器验证；真实 slug 从页面内链接 href 提取（如提升识别准确率 → `improve-asr-accuracy`，预编译热词 → `custom-hot-words`）；官方入口在 QwenLM/Qwen3-ASR README 的 DashScope API Usage 表格 How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
多平台录音转写 API
触发条件
- 用户有录音（课程/会议 MP3/OGG 等）需要转成文字
- 需要对比多家转写引擎质量（写评测文章）
- 用户录音目录：
~/Documents/luyinwenjian/，转写脚本在~/Documents/转写评测/8.7/（2026-08 建） - 视频内容分析：小红书/YouTube 等平台的视频笔记，正文常只有钩子文案，真实内容在视频里 → 下载视频→ffmpeg 抽音频→Gemini 转写。实测 2026-08-14：小红书视频经
opencli xiaohongshu download "<完整URL含xsec_token>"（裸 note_id 会被拒；保存到 cwd 下./xiaohongshu-downloads/<note_id>/），ffmpeg -y -v quiet -i in.mp4 -ac 1 -ar 16000 -b:a 64k out.mp3后，4 分钟视频单段一次转写成功（无需分段）。低成本先试yt-dlp --write-sub --write-auto-sub --skip-download（YouTube 走代理 7897），没字幕再走下载+转写
现成脚本（都在录音目录）
| 脚本 | 用途 |
|---|---|
gemini_transcribe.py |
Gemini 转写（切段→base64→generateContent） |
transcribe_multi.py |
三平台统一入口（`--provider gemini |
bailian_sdk_transcribe.py |
百炼专用（dashscope SDK，本地文件路径） |
三平台调用要点（2026-08 实测）
Gemini
- 模型：
gemini-3.6-flash（gemini-2.5-flash 已对 2026 年新用户关闭，返回 404 "no longer available to new users"） - 端点：
https://generativelanguage.googleapis.com/v1beta/models/{model}:generateContent?key=KEY，inline_data base64 - 免费层充足：72 分钟音频 ≈ 11.5 万 token，转一次 0 元
- 可用模型列表查询：
GET /v1beta/models?key=KEY - Key 文件：
gemini_key.txt - 术语强化：Gemini 没有热词 API，但它是 LLM 解码——把课程术语表写进转写 prompt（"本音频涉及术语：Claude Code、MCP…"）即可起效。干净音频实测术语已 10/10 全对，prompt 术语表只是低成本加成
阿里百炼（坑最多）
- 推荐模型：
qwen3-asr-flash（同步）或qwen3-asr-flash-filetrans（异步，支持 12h/2GB） - OpenAI 兼容模式（chat/completions + input_audio）只接受公网 URL，且请求体限 6.29MB——base64 会被拒（"URL does not appear to be valid"）
- 正解：用 dashscope SDK（
uv run --with dashscope python3 ...），MultiModalConversation.call(model='qwen3-asr-flash', messages=[{'role':'user','content':[{'audio': 本地文件路径}]}])，SDK 自动上传 - 同步接口单段音频上限 240 秒（300 秒报 "The audio is too long"）→ 分段用 3 分钟
- 新版 dashscope SDK 返回 dict 不是对象：
resp.output["choices"][0]["message"]["content"][0]["text"]，用.text会 AttributeError - Key 格式
sk-ws-开头（workspace key），dashscope 兼容端点可用 - Key 文件：
bailian_key.txt - 热词（hotword）：官方支持且免费，但 qwen3-asr-flash 不在热词支持模型列表（支持的是更新的
qwen-audio-3.0-asr-flash系列，且要求北京地域 key +{WorkspaceId}.cn-beijing.maas.aliyuncs.combase URL）。百炼是最需要热词的引擎（锚点实测仅 55%）。完整机制/格式/限制见references/bailian-hotwords.md asr_options官方支持的键：language、enable_lid（语言识别）、enable_itn（数字输出 35%）——走 MultiModalConversation.call 的 **kwargs 透传，SDK 签名里没有显式参数
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 66 lines · 90 tokens per session scan A 83b04db6474b
speech-to-text-apis is a skill published in the GitHub repository bleakbelladonnals/asr-transcription-skills (9 stars, last pushed 25d ago), licensed MIT. It adds 90 tokens to every session and 1,982 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
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…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.