QuillHubDocsBuild with QuillHub
transcription API.
Transcribe audio and video in 98+ languages from your own product. Manage keys, monitor usage, and ship in minutes.
Everything you need to ship transcription
Let your coding agent build the integration
Connect the QuillHub MCP server and your coding agent pulls in the docs (get_developer_docs) and best practices on its own — then wires up the integration for you.
claude mcp add --transport http quillhub https://mcp.quillhub.ai/mcp
Pick your language
curl -X POST https://api.quillhub.ai/v1/transcriptions \-H "Authorization: Bearer $QAI_KEY" \-H "Content-Type: application/json" \-d '{"url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ","speaker_recognition": true,"structure": true}'
Built for real products
Why teams build on QuillHub
Simple, usage-based pricing
Start free, then pay only for what you transcribe. No seat fees, no contracts required.
Frequently asked questions
How do I get an API key?
Sign in, open the Developers dashboard and click "Create key" — you get free credits to test the API right away, no credit card required.
Which audio and video formats are supported?
All common formats — MP3, WAV, M4A, MP4, MOV and more — plus direct YouTube links, which we download and transcribe for you.
How many languages does the API support?
98+ languages with automatic detection, so you don't need to specify the source language up front.
What does it cost, and are there limits?
Start with free credits, then pay only per minute transcribed — no seat fees or contracts. Each request can handle recordings up to 10 hours long.
Does the API support speaker diarization?
Yes. Every transcript is automatically split and labeled per speaker, so you know who said what without extra configuration.
Should I use webhooks or poll for status?
Webhooks are recommended — you're notified the moment a job finishes. Polling the job status endpoint works too if that fits your architecture better.
Can I use the API through an MCP server or coding agent?
Yes. Connect the QuillHub MCP server and your coding agent (Claude, Cursor, etc.) pulls in the docs and best practices on its own, then wires up the integration for you.
What's in the API response?
Beyond the raw transcript, you get clean paragraphs, a table of contents, summary, key highlights and terms — ready to show to end users without further processing.