Remote MCP server that transcribes audio and video into timestamped transcripts and SRT/VTT subtitles, paid per minute in USDC via x402.
What you can do
Quote transcription cost for minutes, bytes or an audio URL, and read paid capacity and pricing status
Mint short-lived single-use upload URLs for local files, then transcribe by upload ID
Transcribe short media synchronously with timestamped segments, SRT/VTT, language detection, word count and duration
Submit long files as async jobs, then poll job status and fetch the transcript or subtitle text
When to use it
Use it when an assistant needs transcripts or subtitle files from audio or video it has the rights to process, including long recordings up to three hours, and when paying per minute in USDC instead of prepaid credits is acceptable.
Requirements
Remote streamable HTTP endpoint; no account, API key or headers declared. A crypto wallet able to pay x402 in USDC on Base is needed for paid calls; free quote and three short jobs per day are available. Local files must be PUT to a signed upload URL over plain HTTP before transcription.
Before you install
Paid tools charge USDC per started minute (sync calls have a 0.003 USDC minimum), and unpaid calls return PaymentRequired. Uploaded media is sent to a third-party service and deleted after transcription or expiry. Platform page URLs such as YouTube or TikTok are refused, and you must hold the rights to the media. Job tokens are shown only once at submit.
Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/dev.moneytools%2Ftranscripts/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.
Paid live status snapshot: capacity remaining today, price table, billing rule, capabilities. 0.001 USDC via x402 over MCP (unpaid → PaymentRequired). Free quote remains at speech_quote / GET /v1/speech/quote.
Takes no parameters.
speech_quote
Free transcript quote
Free: estimate the exact x402 price from minutes, seconds, bytes, or an audio URL (HEAD). Billing uses max(declared, parsed duration, 16 kbps size floor).
Parametersurlbytesminutesseconds
speech_upload_url
Free signed one-time upload URL
Free: mint a short-lived (15 min), single-use PUT URL for local media. PUT the file via plain HTTP (not MCP), then pass upload_id to speech_transcribe. Size cap matches MaxBytes; rate-limited per client. Not a public file host — bytes are deleted after transcription or expiry.
ParametersbytesfilenamecontentType
speech_transcribe
Transcribe audio to text + subtitles
Generate a value-added transcript with timestamped segments, SRT/VTT, language detection, word count and duration (optional summary). 0.002 USDC/started minute (min 0.003); 3 free/day. Pass url, upload_id (from speech_upload_url), or audioBase64 — WAV/MP3/M4A/MP4/WebM/OGG/FLAC you have the right to process. Platform pages refused. Max 10 min / 25 MB. Price = max(declared, parsed, 16 kbps floor).
Free: mint a signed single-use PUT URL for a long file (up to 100 MB / 180 min; MP3/WAV are segmented). PUT via plain HTTP; the PUT response carries the exact price. Then speech_job_submit with uploadId.
Submit a long audio file (url or uploadId) as an async job: 0.002 USDC per started minute (exact, x402 Base USDC), up to 180 min. Without payment returns PaymentRequired with the exact price; pay via _meta["x402/payment"]. First segment is transcribed before settlement; then poll speech_job_status or get a signed webhook.
Free: status, progress and (when done) transcript, segments, SRT/VTT of an async job. Needs jobId + jobToken (shown once at submit). format=srt|vtt|txt returns that text only.
ParametersjobIdrequiredformatjobToken
Version history
1
v1.3.0LatestNov 11, 2026
Score
72%
72% 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 daysRequired25 pts
Auth declaredRequired10 pts
Tools listedRequired15 pts
DescriptionRequired15 pts
Logo10 pts
Publish an icon in the registry entry.
Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
LicenseNot applicable
A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.