Transcribe.soTranscribe.so

Same engine. One HTTP API plus an MCP server.

Drop the transcribe.so API into AI agents, video editors, meeting bots, voice memo apps, and audio pipelines. Same engine that powers the web app, the macOS desktop app, the public ChatGPT GPT, and the Claude Custom Connector. One OpenAPI spec, one MCP endpoint, one Bearer token. Free trial credits on signup, no card required.

No credit card required.·Cancel anytime.

See it in action

Real output from a real transcription

Browse chapters, ask questions, and explore search results from an actual transcript.

How to Quit Your Job (and Find Work You Actually Love)
Ali Abdaal
Contents
18 chapters · 57 sections
1Why I quit my high-paying job with no plan
2The shame of walking away from success
3Stop accepting low-grade suffering at work
4Are you wired for the pathless path?
5The math behind quitting your job safely
6Use time off to rediscover who you are
7How to fund your freedom on a budget
8Your income streams will evolve over time
9Turn your skills into immediate cash flow
10Treat your career break like a life MBA
11Passion doesn't mean work is easy
12Align your daily actions with your ideal life
13Focus on your mode, not your niche
14Declare yourself retired with the skip test
15Handling family criticism of your career choices
16Would you trade wealth for total freedom?
17Get comfortable with feeling cringe
18Why traditional job security is a myth
Ask this video
Answer
Paul left because the work had quietly stopped fitting who he was, not because of a single dramatic event. Early on he chased prestige and big salaries, optimizing for impressive internships and the markers of success [00:59–02:18]. By around thirty-two the job had drained his energy and passion, and quitting was mostly about escaping that misalignment and getting himself back [04:37–06:04]. When he ran a self-assessment, he realized he'd drifted from the goals he set in grad school, to avoid becoming money-obsessed and to keep his sense of humor, which made clear how far off course he'd gone [06:05–07:55]. The decision was less “follow your dream” and more “stop betraying your own values.”

Command Palette

Search for a command to run...

Building audio infrastructure is not the project you want to be on

  • Managed transcription APIs cap at 25 MB and rate-limit the moment you scale past hobby use
  • English-first models without per-language routing tax multilingual workloads
  • Self-hosted Whisper-large eats GPU budget and breaks on long files or non-English audio
  • Polling every few seconds blocks workers and burns rate-limit budget you'd rather spend on real traffic

What you get from the transcribe.so API and MCP server

One Bearer token, three input shapes

POST a YouTube URL, an external audio link, or a file uploaded via presigned S3 PUT. Same response shape regardless. No SDK required; pure HTTP.

MCP server for Claude and ChatGPT

Drop-in for Claude Desktop, ChatGPT Custom GPTs, and any MCP-compatible client. Exposes transcribe, search_library, list_transcriptions, and get_me tools out of the box.

Webhooks, not polling

Register a URL and we POST you when transcription completes. HMAC-signed (Stripe-style). Auto-retry with exponential backoff. Works with Cloudflare Workers, Lambda, Vercel, n8n, any HTTP-capable runtime.

Multilingual without compromise

67 languages with measured accuracy per language. The right ASR engine is picked per request, or you specify. Same engine routes the consumer dashboard.

Structured outputs, not raw text

/result returns segments, word-level timestamps, speaker labels, chapters, topics, summaries, and cited Q&A, not a wall of text. Skip the post-processing pipeline you'd otherwise build on top of raw ASR.

Predictable retries, debuggable failures

Idempotency-Key header support. Stripe-style error envelope with code, message, request_id, and doc_url. Per-key spend visibility in the dashboard.

What people use this for

  • AI agents that read audio, drop transcripts into your LLM context and let agents reason over hours of recordings
  • Meeting bots, process Zoom and Twilio recordings into searchable notes the moment a call ends
  • Voice memo apps on iPhone and Android, auto-generated chapters and topics from raw audio
  • Podcast pipelines, process new episodes from RSS feeds into show notes and chapter posts
  • Video editors, generate burn-in captions with word-level timestamps, export SRT and VTT directly
  • Language learning apps, accurate multilingual transcripts for shadowing and dictation drills
  • Customer support, surface call topics and follow-ups from recorded calls
  • Journalist workflows, drop interview audio in, get back chapters, quotes, and a searchable archive

FAQ

Frequently asked questions

The HTTP API is for any backend or script that can make Bearer-authenticated HTTP calls. The MCP server is for LLM agents (Claude Desktop, ChatGPT Custom GPTs, Cursor, and other MCP-capable clients) that want transcription and library tools surfaced as native MCP actions. Same engine, different surface.

Free to start, then unlimited transcription on Pro at $19/mo or Business at $49/mo on our own engine. Premium models like GPT-4o and Voxtral are billed per minute from your wallet at the same rates as the consumer dashboard, only when you choose them. No file-size caps; presigned uploads support files up to 500 MB. Multilingual workloads are not separately taxed.

Free trial credits on signup. Enough to transcribe roughly a couple of hours on Qwen3-ASR-Flash. No card required. Top up the wallet from the billing page when you're ready to scale.

Yes. Bearer auth means no cookies and no CSRF. CORS is open on every /api/v1/ endpoint. Webhooks remove the need for long-running polling. Works from Cloudflare Workers, Lambda, Vercel, edge functions, n8n, and anything that can make an HTTP call.

67 languages with FLEURS-measured accuracy per language and per pipeline. Set language: 'auto' to let the engine detect and route, or specify a pipeline to lock in a model.

Three options. (1) Add the MCP server to Claude Desktop or a ChatGPT Custom GPT and the transcription tools appear natively. (2) Use Bearer-authenticated HTTP from any agent framework. (3) Use the public ChatGPT app or Claude connector and the engine works out of the box.

POST /api/v1/transcriptions returns 402 insufficient_funds with a doc_url pointing to the billing page. In-flight jobs complete normally. Top up and retry. Idempotency keys prevent duplicate submissions.

X-Transcribe-Signature header carries t=<unix-seconds>,v1=<hmac_sha256(secret, '${t}.${rawBody}')>. Verify against the raw request body. TypeScript and Python examples at /developers/docs#webhooks.

500 MB per file via presigned upload. No length cap; long audio is chunked internally. A 4-hour podcast transcribes in 4–8 minutes wall time on Qwen3-ASR-Flash.

Want a deeper comparison? Read the launch announcement

Ship it today.

Create a key, paste it into your script, transcribe in a minute. Or add the MCP server to Claude Desktop or your ChatGPT GPT. Per-key spend visibility and webhook configuration in the dashboard.