Edge API
The Edge API is a synchronous speech-to-text API for short audio. It transcribes a short audio or video file in one request. You upload the file, and the transcript comes back in the same response, so there's nothing to poll and no webhook to receive. Use it for short recordings when you want the result right away, including from browser code. For long or large files, or when you need speaker parsing, audio labels, subtitles, or webhooks, use the Jobs API. How to Transcribe with Speech is Cheap compares all the APIs.
Base URL
All requests go to https://edge.speechischeap.com.
Authentication
Send your API key as a Bearer token in the Authorization header. Edge accepts the same API keys as the Jobs API.
Authorization: Bearer YOUR_API_KEY
Choose a plan on Pricing to get a key. Your first key arrives by email, and you manage keys in the Dashboard.
Endpoints
| Method | Path | Page |
|---|---|---|
POST | /v2/jobs/ | Upload a File |
GET | /v2/jobs/health | API Health |
GET | /v2/jobs/auth | API Health |
Job States
Every 200 response to an upload has one of these status values:
| Status | Meaning |
|---|---|
COMPLETED | The transcription finished. The transcript is in output. |
FAILED | The transcription failed. output.error says why. You aren't charged. |
Edge answers both with HTTP 200, so always check status. See Response.
How Results Arrive
The transcript arrives in the response to the upload, and the connection stays open until transcription finishes. Edge has no webhooks, no event stream, and no endpoint for reading a job later, so keep the response.