{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_jrgbn7c23eqj","handle":"audio-transcribe-cli-mcp","url":"https://wellknown.network/agents/audio-transcribe-cli-mcp","links":{"self":"https://wellknown.network/agents/audio-transcribe-cli-mcp/record.json","html":"https://wellknown.network/agents/audio-transcribe-cli-mcp","markdown":"https://wellknown.network/agents/audio-transcribe-cli-mcp/record.md","api":"https://wellknown.network/api/v1/agents/audio-transcribe-cli-mcp","status":"https://wellknown.network/api/v1/agents/audio-transcribe-cli-mcp/status","claim":"https://wellknown.network/agents/audio-transcribe-cli-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/audio-transcribe-cli-mcp/claim.json","badge":"https://wellknown.network/agents/audio-transcribe-cli-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/audio-transcribe-cli-mcp/history","tools":"https://wellknown.network/api/v1/agents/audio-transcribe-cli-mcp/tools"},"ard":{"identifier":"urn:air::server:audio-transcribe-cli-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"audio-transcribe-cli-mcp","summary":"音视频转文字 CLI / MCP Server：阿里云百炼录音文件识别，支持说话人分离与微信语音 SILK","description":"# audio-transcribe-cli-mcp \n \n**音视频转文字，支持 CLI、MCP Server 两种形态：说话人分离，长音频免切片，原生支持微信语音 SILK 格式。** \n \nAudio/video transcription in both CLI and MCP Server flavors: speaker diarization, long-audio support with no manual splitting, and native WeChat SILK decoding. \n \n[English](README_EN.md) | 简体中文 \n \n基于阿里云百炼录音文件识别接口（qwen-audio-asr 系列 / paraformer）。不依赖 Claude Code：可作为独立命令行工具，也可接入任意 MCP 客户端（Claude Desktop、Cursor 等）。 \n \n## 功能特性 \n \n- **全格式输入**：mp3 / wav / m4a / aac / flac / ogg / opus / amr / wma 及 mp4 / mkv / mov 等所有 ffmpeg 支持的音视频格式（视频自动抽取音轨） \n- **微信语音 SILK 原生支持**：自动识别并剥离微信 `0x02 + #!SILK_V3` 文件头，通过 [uv](https://docs.astral.sh/uv/) 临时环境调用 [pilk](https://github.com/foyoux/pilk) 解码（仅转写 silk 文件时需要 uv，其余格式零额外依赖） \n- **说话人分离**：多人对话按 `说话人N：内容` 分段输出；单一说话人自动退化为整段纯文本 \n- **句级时间戳**：`--timestamps` 逐句输出 SRT 风格起止时间戳，AI 生成会议纪要后可按时间戳回原音频核对 \n- **长音频免切片**：走百炼录音文件识别（filetrans）异步接口，一次上传整段处理，DashScope 临时存储转完自动删除 \n- **清晰的输出约定**：stdout 只输出转写文本，进度 / 耗时 / 计费估算走 stderr，方便脚本和 Agent 调用 \n- **内置 MCP Server**：`audio-transcribe-mcp` 命令，手写 MCP stdio 协议（JSON-RPC 2.0），仅标准库零第三方依赖，任意 MCP 客户端即插即用 \n \n## 安装 \n \n```bash \npip install audio-transcribe-cli-mcp \n``` \n \n也可从源码安装： \n \n```bash \ngit clone https://github.com/OstrichHermit/audio-transcribe-cli-mcp.git \ncd audio-transcribe-cli-mcp \npip install . \n``` \n \n安装后会得到两个命令：`asr`（CLI）和 `audio-transcribe-mcp`（MCP Server）。 \n \n### 安装为 Agent Skill（可选） \n \n仓库内附带 Agent Skill（`skills/audio-transcribe-cli-mcp/SKILL.md`），把它复制到你所用 AI Agent 的 skills 目录，Agent 即可自动掌握本工具的用法。以 Claude Code 为例： \n \n```bash \ncp -r skills/audio-transcribe-cli-mcp ~/.claude/skills/audio-transcribe-cli-mcp \n``` \n \n### 1. 安装依赖 \n \n- Python 3.10+（`pip install .` 会自动安装 dashscope 依赖） \n- [ffmpeg / ffprobe](https://ffmpeg.org/) 自行安装并加入 PATH \n- 仅转写微信 SILK 文件时额外需要 [uv](https://docs.astral.sh/uv/)（脚本自动创建 Python 3.11 临时环境安装 pilk，无需手动操作） \n \n### 2. 配置 API Key \n \n在[阿里云百炼控制台](https://bailian.console.aliyun.com/)创建 API Key，配置到环境变量： \n \n```bash \n# Windows \nsetx DASHSCOPE_API_KEY \"sk-xxxx\" \n \n# macOS / Linux \necho 'export DASHSCO…","publisher":{"name":"OstrichHermit","url":null},"homepage":"https://github.com/OstrichHermit/audio-transcribe-cli-mcp","repository":"https://github.com/OstrichHermit/audio-transcribe-cli-mcp","version":"0.1.2","license":"MIT","protocols":["mcp"],"tags":["asr","speech-to-text","transcription","dashscope","qwen","audio","video","mcp","whisper-alternative"],"pricing":null,"endpoints":[{"url":"pypi:audio-transcribe-cli-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"media.speech-recognition","name":"Speech Recognition","confidence":1,"provenance":"declared"},{"slug":"dev.version-control","name":"Version Control","confidence":0.745,"provenance":"derived"}],"categories":["dev","media"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"audio-transcribe-cli-mcp","registry":"pypi","observedAt":"2026-10-30T19:26:46.161Z","publishedAt":"2026-10-08T09:56:58.405486Z","latestVersion":"0.1.2"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"audio-transcribe-cli-mcp","url":"https://pypi.org/project/audio-transcribe-cli-mcp/","firstSeenAt":"2026-10-06T13:22:30.974Z","fetchedAt":"2026-10-30T19:24:46.301Z","normalizedAt":"2026-10-30T19:24:46.301Z"}]},"firstSeenAt":"2026-10-06T13:22:30.974Z","updatedAt":"2026-10-30T19:26:46.161Z"}