
Transcribe Mcp
io.github.Soboljem由 GitHub 账号 Soboljem 发布v0.1.1更新于 Oct 27, 2026
Transcribe audio/video and find dead air. Pay-per-call in USDC over x402 — no account, no key.
发布方自己的服务:Transcribe
概览
本地 MCP 服务器:转写音视频、找出静音片段、把网页转为 markdown,按次用自有钱包中的 USDC 付费。
- 可以做什么
- 把公开音视频链接或本地音频文件转写为文本、时间轴和识别语言
- 根据字幕或时间轴找出可剪掉的静音区间并估算可节省比例
- 抓取网页并转为干净的 markdown,可选择渲染 JavaScript 页面
- 免费查询价格、限制和支付方式
- 把大结果保存到新的 JSON 文件,回复保持简短
- 适用场景
- 适合需要转写文本、为剪辑寻找静音片段或提取网页正文的场景,且希望按次支付几分钱而不注册 API 密钥。更适合偶发的串行任务,而非高并发批量使用。
- 运行要求
- 通过 npx 在本机运行,需要 Node 20+;视频流程还需要 ffmpeg。付费工具需要环境变量 TRANSCRIBE_MCP_WALLET_KEY 提供持有少量 Base 链 USDC 的钱包私钥,不设置也能启动并查看价格。需要访问服务商端点的网络。Windows 上需用 cmd 包装 npx。
安装
在 SourceWeft 中
- 打开 控制台中的 Transcribe Mcp,将其添加到工作区。
- 为需要使用其工具的对话启用该服务。
Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。
其他 MCP 客户端
参照 仓库 中的启动说明。
README
transcribe-mcp
Read web pages as clean markdown, transcribe audio and video, and find the silence worth cutting — from any MCP client. No account, no API key, no subscription. Your agent pays a fraction of a cent per call, in USDC, straight from a wallet you control.
On Windows, MCP clients can't start npx directly, so wrap it:
"command": "cmd", "args": ["/c", "npx", "-y", "transcribe-mcp@latest"].
That is the whole setup. There is nothing to sign up for. It needs Node 20+. The video skill also needs ffmpeg.
One paid call at a time per wallet. The shop refuses a second paid request while one is still running (free, with "already in flight"). Call it sequentially, never in parallel.
Tools
find_dead_air eats exactly what transcribe_url returns, so the two chain:
transcribe a talk, then cut the silence out of it.
transcribe_url and find_dead_air take save_to: an absolute path to a new .json file. The full result
goes there and the reply is one line plus the receipt, so an hour of transcripts never floods
your agent's context. It never overwrites a file, and a missing folder is refused before paying.
Cutting a whole video
For cutting a whole video end to end — split, transcribe, cut, synced subtitles — there is a
ready agent skill in skills/dead-air-cutter.
What leaves your machine
transcribe_url: theurl, or the bytes of thefile(audio only —.mp3 .wav .m4a .aac .ogg .opus .oga .flac; a video is refused, extract its audio with ffmpeg first).find_dead_air: the timings and text — fromfrom_file, onlystart,end,textof each segment plusdurationSecondsare sent, whatever else the file holds. If the file has avttfield instead, that subtitle text is sent whole.fetch_page: the page URL.
This server talks only to https://transcribe.soboljem.cz. What the shop does with it, from its
terms:
- Audio is never stored. It is transcribed by Cloudflare Workers AI and passes through Cloudflare's infrastructure.
- The result is kept briefly, up to about 8 hours. It is replayable for 15 minutes, then deleted by a sweep that runs four times a day. The replay is a shop-side safeguard that this client cannot use: every call signs a new payment. After a timeout or a "may have been charged" reply, check the wallet. Calling again pays again.
- A row per sale is kept with no automatic deletion: time, price, audio length, word and cut counts, the source hostname (never the full URL), and the paying wallet address and transaction hash, which are public on Base anyway. Ask via the terms page to have rows deleted.
- Payment settles through the PayAI facilitator on Base. On each sale, the shop owner gets a Telegram notification with the shortened payer address and source hostname.
The private key in TRANSCRIBE_MCP_WALLET_KEY never leaves the machine. It only signs.
Why pay-per-call instead of an API key
Because an agent cannot fill in a signup form. x402 is an HTTP-native
payment: the server answers 402 Payment Required with a price, the client pays it, the
request goes through. No dashboard, no key rotation, no minimum, no monthly bill. If you
never call it, you never pay anything.
Settlement is USDC on Base (eip155:8453).
Running it without a wallet
It starts fine. shop_info answers, tools/list works, and the paid tools tell you what
to set. Look before you fund anything.
What it will not do
- It will not overspend. Every call is filtered through a $0.10 ceiling; a quote above it is dropped and the client refuses to pay rather than guessing.
- It will not charge you for a refusal. Bad arguments are caught locally and never leave your machine. The shop is built not to settle error responses; that was verified on testnet (see its terms).
- It will not tell you "no charge" when it cannot know. If the connection drops mid-call, it says a payment may have gone out and to check the wallet before calling again.
- It will not lie about a sale. If the settlement header is missing, it says so instead of reporting a payment it cannot prove.
Files are capped at 800 KB. Oversized ones are refused for free, before payment.
A local file is sent to the shop as bytes, so nothing has to be hosted first. For anything
long, extract the audio small and split it — mono Opus at 16 kbps fits ~6 minutes per call:
Configuration
Use a dedicated wallet with a few dollars in it, not your main one. This is true of every tool you hand a private key to, and it is true here.
Tests
MIT.
来源:README.md,提交 ba83615
工具
0版本历史
1- v0.1.1最新Sep 16, 2026
评分
已满足适用检查项的 50%
该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。
- 近 30 天内可连通25 分
请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。
- 已声明认证方式10 分
请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。
- 已列出工具15 分
请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。
- 描述必需15 分
- 图标10 分
- 文档15 分
- 许可证10 分
其他 Transcribe 集成
Transcribe
so.transcribe官方发布者
Transcribe 让助手通过托管远程端点把音视频转成带说话人标注的转录稿、字幕、片段和带引用的问答。

Verbatim Transcribe
由 GitHub 账号 xyzxinlu-max 发布
让助手驱动本机 Verbatim 服务,提交音视频转写、查询任务进度并搜索转写库。

OpenTranscribe MCP
由 GitHub 账号 fbossiere 发布
OpenTranscribe 通过 MCP 把音频文件或 HTTPS 链接交给所选语音转写服务,并返回统一的转写结构。

vocce transcribe
由 GitHub 账号 cmoonagent 发布
一个本地 MCP 服务器,让助手转写音视频、生成摘要、笔记和闪卡、基于文档问答,并压缩 PDF。

Whisper Transcribe
由 GitHub 账号 ZahiriNatZuke 发布
让助手使用本地 faster-whisper 或 OpenAI Whisper API 转写音频文件。