Fulcrum API

curl -X POST https://api.fulcrumgo.com/api/v1/transcribe-audio \
  -H "Authorization: Bearer mcpsk_<your_api_key>" \
  -H "Content-Type: application/json" \
  -d '{
  "audio_url": "",
  "language": "en"
}'

Add this server to Claude Desktop's claude_desktop_config.json. The endpoint becomes a callable tool inside Claude. See the MCP setup guide for the full walk-through.

{
  "mcpServers": {
    "this-api": {
      "url": "https://api.fulcrumgo.com/mcp",
      "transport": "http",
      "auth": {
        "type": "bearer",
        "token": "mcpsk_<your_api_key>"
      }
    }
  }
}

Inside Claude this endpoint surfaces as the tool transcribe-audio.

Standard requests — no custom SDK needed. pip install requests first.

import requests

r = requests.post(
    "https://api.fulcrumgo.com/api/v1/transcribe-audio",
    headers={"Authorization": "Bearer mcpsk_<your_api_key>"},
    json={
  "audio_url": "",
  "language": "en"
},
)
r.raise_for_status()
print(r.json())

Plain fetch. Works in Node 18+, Deno, Bun, and any modern browser.

const r = await fetch("https://api.fulcrumgo.com/api/v1/transcribe-audio", {
  method: "POST",
  headers: {
    "Authorization": "Bearer mcpsk_<your_api_key>",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
  "audio_url": "",
  "language": "en"
}),
});
if (!r.ok) throw new Error(`HTTP ${r.status}`);
console.log(await r.json());

Input

Field	Type	Required	Default	Description
audio_url	string	required	—	Public URL of the audio file to transcribe (mp3/wav/m4a/…). maxLength=2083 minLength=1 format=uri
language	string	optional	en	BCP-47 language hint (e.g. en, es, ar). Provider may auto-detect. maxLength=16

Output

Field	Type	Required	Default
job_id	string	required	—
status	string	required	—
status_url	string	required	—

Try it

Fires a real POST /api/v1/transcribe-audio from your browser. Charges 2 credits per call against your account.