Pepys Mcp
Pay-as-you-go audio & video transcription with diarization + AI. Transcribe, podcast feeds, SRT/VTT export, search – BYO key or hosted OAuth connector. Never trains on your audio.
Overview
API
Transcription API
Transcribe any audio, video, or podcast programmatically – over the REST API, or as an MCP server so AI agents transcribe on their own. Async jobs with polling or webhooks, and native podcast (RSS / Apple) support.
MCP – give an AI agent Pepys
Want the short version? See the MCP server page. Full setup below.
Let an AI agent (Claude, ChatGPT, Cursor, and other MCP clients) transcribe on its own – hours-long files, diarization, correctly-timed SRT/VTT, paste-a-link, whole podcast feeds, and search across a transcript – over the Model Context Protocol. Two ways to connect:
1. Hosted connector – no API key
Point a remote MCP connector at https://pepys.co/api/mcp. The agent signs in to Pepys once (OAuth); transcription bills to your credits. In Claude: Settings → Connectors → Add custom connector. Best for Claude and ChatGPT.
2. Local server – your own key
Run the published pepys-mcpserver with your API key – best for local dev agents. Add to your client's MCP config:
{
"mcpServers": { "pepys": { "command": "npx", "args": ["-y", "pepys-mcp"], "env": { "PEPYS_API_KEY": "pk_live_your_key" } } } }
Both expose the same tools – transcribe, get_transcription, upload_file, export_transcript, transcribe_podcast_feed, search_transcript, and get_credit_balance. The 60 free minutes on signup apply; diarization, whole-feed batch, and word-level export unlock with any one-time purchase.
Pepys is listed on Smithery, mcp.so, and the MCP Registry.
Authentication
Create a key under Settings → API keys (shown once). Send it as a bearer token. All endpoints are under https://pepys.co/api/v1.
curl https://pepys.co/api/v1/transcriptions
-H "Authorization: Bearer pk_live_your_key"Usage draws from your account credit balance (1 credit = 1 minute). Enable auto-reload for unattended jobs so they don't pause at a zero balance.
Create a transcription
POST /api/v1/transcriptions
Pass exactly one source: a remote url (audio/video file, podcast RSS or Apple link, or a social link), a media_ref from a direct upload, or a public blob_url.
curl -X POST https://pepys.co/api/v1/transcriptions
-H "Authorization: Bearer pk_live_…"
-H "Idempotency-Key: my-unique-id"
-H "Content-Type: application/json"
-d '{ "url": "https://example.com/episode.mp3", "diarize": true, "summary": true, "language": "en" }'
→ 202 { "id": "…", "status": "queued", "url": "/api/v1/transcriptions/…" }
Options
language– ISO code; omit to auto-detect.diarize– detect speakers (billed at 3× on long-form).summary,chapters– AI extras.translate_to– ISO code to also return a translation.quality–fast|accurate.
Reuse an Idempotency-Key to make retries safe. A cached or caption-backed source returns 200 with status: "done" immediately.
Get a transcription
GET /api/v1/transcriptions/{id}
Poll until status is done (or failed), or use a webhook instead.
{
"id": "…", "status": "done", "language": "en", "duration_seconds": 1771, "word_count": 4120, "billed_minutes": 30, "text": "Full transcript…", "summary": "…", "segments": [ { "start": 0.0, "end": 4.2, "speaker": "Speaker 1", "text": "Welcome back." } ] }
List with GET /api/v1/transcriptions.
Podcasts
A podcast is an RSS feed; each episode's audio is its <enclosure>. Pass a feed URL (or an Apple Podcasts link) as urlto transcribe its latest episode, or list episodes first and transcribe a specific one's audio_url.
GET /api/v1/podcasts/episodes?feed={rss_url}&limit=50
curl "https://pepys.co/api/v1/podcasts/episodes?feed=https://feeds.simplecast.com/54nAGcIl&limit=3"
-H "Authorization: Bearer pk_live_…"→ { "total": 2900, "returned": 3, "data": [ { "title", "guid", "published_at", "duration_seconds", "audio_url" } ] }
transcribe a specific episode by guid (no need to pass the audio_url):
curl -X POST https://pepys.co/api/v1/transcriptions
-H "Authorization: Bearer pk_live_…"
-d '{ "url": "<feed_url>", "episode_guid": "<guid>" }'
(or "episode_index": 0 for the newest, 1 for the next, …)
Transcribe a whole feed
Fan a feed out into one transcription per episode (grouped as a batch).
POST /api/v1/podcasts/transcribe
curl -X POST https://pepys.co/api/v1/podcasts/transcribe \-H "Authorization: Bearer pk_live_…"
-d '{ "feed": "<feed_or_apple_url>", "episodes": "all", "diarize": true }'
episodes: "latest" (default) | "all" | <number>
→ 202 { "batch_id": "…", "total": 42, "transcriptions": [ { "id", "title", "guid", "url" } ] }
Each returned transcription id is polled (or webhook-notified) like any other.
Direct uploads
For your own files, get a presigned URL, PUT the bytes, then transcribe the returned media_ref.
POST /api/v1/uploads
# 1. handshakecurl -X POST https://pepys.co/api/v1/uploads
-H "Authorization: Bearer pk_live_…"
-d '{ "filename": "call.mp3", "content_type": "audio/mpeg", "bytes": 5242880 }'
→ { "upload_url": "https://…", "media_ref": "uploads/<you>/<uuid>.mp3", "expires_in": 600 }
2. upload the bytes (Content-Type + Content-Length must match)
curl -X PUT "<upload_url>" -H "Content-Type: audio/mpeg" --data-binary @call.mp3
3. transcribe it
curl -X POST https://pepys.co/api/v1/transcriptions
-H "Authorization: Bearer pk_live_…"
-d '{ "media_ref": "uploads/<you>/<uuid>.mp3" }'
Webhooks
Register an endpoint under Settings → Webhooks (or POST /api/v1/webhooks) to receive a signed POST on transcription.completed and transcription.failed – no polling.
POST https://your-server.com/webhooks/pepys Pepys-Event-Type: transcription.completed Pepys-Event-Id: <jobId>.done Pepys-Signature: t=1718800000,v1=<hmac-sha256-hex>
{ "id": "<jobId>.done", "type": "transcription.completed", "created": 1718800000, "data": { "transcription": { "id": "…", "status": "done", "url": "https://pepys.co/api/v1/transcriptions/…" } } }
Verify the signature
Recompute HMAC-SHA256 over {timestamp}.{rawBody}v1 value.
import { createHmac, timingSafeEqual } from "node:crypto";
function verify(rawBody, header, secret) { const { t, v1 } = Object.fromEntries(header.split(",").map((p) => p.split("="))); const expected = createHmac("sha256", secret).update(${t}.${rawBody}).digest("hex"); const ok = v1.length === expected.length && timingSafeEqual(Buffer.from(v1), Buffer.from(expected)); if (!ok) throw new Error("bad signature"); // Optional: reject if Math.abs(Date.now()/1000 - Number(t)) > 300 (replay window). return JSON.parse(rawBody); }
Respond 2xx within 10s. Non-2xx / timeouts retry with backoff (up to 6 attempts). The payload carries a summary; fetch the full transcript via GET /api/v1/transcriptions/{id}.
Errors & limits
401– missing/invalid key.402– out of credits (top up / enable auto-reload).400 / 422– bad params or an unresolvable link.429– rate limited (aRetry-Afterheader is included).
Clips for social are capped at 90s; transcription length follows your plan limits.
{timestamp}.{rawBody}"}]," with your endpoint secret and constant-time compare against the ",["$","code",null,{"className":"font-mono text-xs","children":"v1"}]," value."]}],["$","pre",null,{"className":"mt-3 overflow-x-auto rounded-xl border border-line bg-band p-4 font-mono text-[13px] leading-relaxed text-ink","children":["$","code",null,{"children":"import { createHmac, timingSafeEqual } from \"node:crypto\";\n\nfunction verify(rawBody, header, secret) {\n const { t, v1 } = Object.fromEntries(header.split(\",\").map((p) =\u003e p.split(\"=\")));\n const expected = createHmac(\"sha256\", secret).update(${t}.${rawBody}).digest(\"hex\");\n const ok = v1.length === expected.length \u0026\u0026\n timingSafeEqual(Buffer.from(v1), Buffer.from(expected));\n if (!ok) throw new Error(\"bad signature\");\n // Optional: reject if Math.abs(Date.now()/1000 - Number(t)) \u003e 300 (replay window).\n return JSON.parse(rawBody);\n}"}]}],["$","p",null,{"children":["Respond ",["$","code",null,{"className":"font-mono text-xs","children":"2xx"}]," within ",10,"s. Non-2xx / timeouts retry with backoff (up to 6 attempts). The payload carries a summary; fetch the full transcript via"," ",["$","code",null,{"className":"font-mono text-xs","children":"GET /api/v1/transcriptions/{id}"}],"."]}]]}]]}]\n"]), follow"}],["$","meta","8",{"name":"googlebot","content":"index, follow, max-video-preview:-1, max-image-preview:large, max-snippet:-1"}],["$","link","9",{"rel":"canonical","href":"https://pepys.co/developers"}],["$","meta","10",{"name":"format-detection","content":"telephone=no, address=no, email=no"}],["$","meta","11",{"property":"og:title","content":"Transcription API – Developer Docs | Pepys"}],["$","meta","12",{"property":"og:description","content":"Programmatic audio, video, and podcast transcription. API keys, a single transcriptions endpoint, podcast RSS support, direct uploads, and signed webhooks."}],["$","meta","13",{"property":"og:url","content":"https://pepys.co/developers"}],["$","meta","14",{"property":"og:site_name","content":"Pepys"}],["$","meta","15",{"property":"og:locale","content":"en_US"}],["$","meta","16",{"property":"og:image","content":"https://pepys.co/opengraph-image"}],["$","meta","17",{"property":"og:image:type","content":"image/png"}],["$","meta","18",{"property":"og:image:width","content":"1200"}],["$","meta","19",{"property":"og:image:height","content":"630"}],["$","meta","20",{"property":"og:image:alt","content":"Pepys – transcribe audio and video to text, pay as you go"}],["$","meta","21",{"property":"og:type","content":"website"}],["$","meta","22",{"name":"twitter:card","content":"summary_large_image"}],["$","meta","23",{"name":"twitter:title","content":"Transcription API – Developer Docs | Pepys"}],["$","meta","24",{"name":"twitter:description","content":"Programmatic audio, video, and podcast transcription. API keys, a single transcriptions endpoint, podcast RSS support, direct uploads, and signed webhooks."}],["$","meta","25",{"name":"twitter:image","content":"https://pepys.co/opengraph-image"}],["$","meta","26",{"name":"twitter:image:alt","content":"Pepys – transcribe audio and video to text, pay as you go"}],["$","meta","27",{"name":"twitter:image:type","content":"image/png"}],["$","meta","28",{"name":"twitter:image:width","content":"1200"}],["$","meta","29",{"name":"twitter:image:height","content":"630"}],["$","link","30",{"rel":"icon","href":"/favicon.ico?favicon.21rrjd57gty57.ico?dpl=dpl_8xFFCU88gTSYLbNfJx9g8HgaifDc","sizes":"192x192","type":"image/x-icon"}],["$","link","31",{"rel":"icon","href":"/icon.png?icon.3fc1av3cchcq2.png?dpl=dpl_8xFFCU88gTSYLbNfJx9g8HgaifDc","sizes":"512x512","type":"image/png"}],["$","link","32",{"rel":"icon","href":"/icon.svg?icon.0c71tfnb726pg.svg?dpl=dpl_8xFFCU88gTSYLbNfJx9g8HgaifDc","sizes":"any","type":"image/svg+xml"}],["$","link","33",{"rel":"apple-touch-icon","href":"/apple-icon.png?apple-icon.39wkgwp4xbxbk.png?dpl=dpl_8xFFCU88gTSYLbNfJx9g8HgaifDc","sizes":"180x180","type":"image/png"}],["$","$L38","34",{}]]\n"])Server Config
{
"mcpServers": {
"pepys": {
"command": "npx",
"args": [
"-y",
"pepys-mcp"
],
"env": {
"PEPYS_API_KEY": "<YOUR_PEPYS_API_KEY>"
}
}
}
}Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
Tavily Mcp
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
Playwright McpPlaywright MCP server
Serper MCP ServerA Serper MCP Server
CursorThe AI Code Editor
WindsurfThe new purpose-built IDE to harness magic
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
Baidu Map百度地图核心API现已全面兼容MCP协议，是国内首家兼容MCP协议的地图服务商。
ChatWiseThe second fastest AI chatbot™
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
Howtocook Mcp基于Anduin2017 / HowToCook （程序员在家做饭指南）的mcp server，帮你推荐菜谱、规划膳食，解决“今天吃什么“的世纪难题；
Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
Y GuiA web-based graphical interface for AI chat interactions with support for multiple AI models and MCP (Model Context Protocol) servers.
DeepChatYour AI Partner on Desktop
RedisA Model Context Protocol server that provides access to Redis databases. This server enables LLMs to interact with Redis key-value stores through a set of standardized tools.
Amap Maps高德地图官方 MCP Server