
Transcribe Mcp
io.github.SoboljemPublished by GitHub account Soboljemv0.1.1Updated Oct 27, 2026
Transcribe audio/video and find dead air. Pay-per-call in USDC over x402 — no account, no key.
The publisher's own server: Transcribe
Overview
Local MCP server that transcribes audio and video, finds dead air, and converts web pages to markdown, paid per call in USDC from your own wallet.
- What you can do
- Transcribe a public audio/video URL or a local audio file into text, timings and detected language
- Find dead air and cut-worthy silence spans from subtitles or timings, with estimated savings
- Fetch a web page as clean markdown, optionally rendering JavaScript pages
- Show shop prices, limits and payment details for free
- Save large results to a new JSON file so replies stay short
- When to use it
- Useful when an assistant needs transcripts, silence detection for editing, or clean page text, and you would rather pay a few cents per call than sign up for an API key. It suits occasional, sequential jobs rather than high-volume parallel use.
- Requirements
- Runs locally via npx, so Node 20+ is needed; the video workflow also needs ffmpeg. A wallet private key in TRANSCRIBE_MCP_WALLET_KEY holding a little USDC on Base is required only for paid tools; the server starts and lists prices without it. Network access to the provider's endpoint is required. On Windows, npx must be wrapped with cmd.
Installation
In SourceWeft
- Open Transcribe Mcp in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
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.
Source: README.md at commit ba83615
Tools
0Version history
1- v0.1.1LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Other Transcribe integrations
Transcribe
so.transcribeOfficial publisher
Transcribe lets an assistant turn audio and video into speaker-labelled transcripts, subtitles, clips, and cited Q&A through a hosted remote endpoint.

Verbatim Transcribe
Published by GitHub account xyzxinlu-max
Lets an assistant drive a local Verbatim service to transcribe audio and video, poll jobs, and search a transcript library.

OpenTranscribe MCP
Published by GitHub account fbossiere
OpenTranscribe routes audio files or HTTPS URLs to a chosen speech-to-text provider and returns one normalized transcript schema over MCP.

vocce transcribe
Published by GitHub account cmoonagent
A local MCP server that lets an assistant transcribe audio and video, summarize, make notes and flashcards, answer questions about documents, and compress PDFs.

Whisper Transcribe
Published by GitHub account ZahiriNatZuke
Lets an assistant transcribe audio files locally with faster-whisper or through the OpenAI Whisper API.