Speech to Text

Upload an audio file once, get a task id immediately, then read the transcript from the common task result when processing finishes.

Endpoint

http

POST https://api.cheapaiapi.com/v1/task/speech-to-text

Send this request as multipart/form-data.

Request Fields

filefilerequiredAudio file such as mp3, aac, aiff, ogg, opus, wav, webm, flac, or m4a.

receive_urlstringOptional webhook URL for transcript delivery.

Example Request

bash

curl -X POST "https://api.cheapaiapi.com/v1/task/speech-to-text" \
  -H "Authorization: Bearer sk_your_api_key" \
  -F 'file=@recording.mp3' \
  -F 'receive_url=https://your-app.com/webhooks/transcripts'

Task Pattern

json

{
  "success": true,
  "task_id": "uuid_task_id",
  "ec_remain_credits": 123456
}

Use the common task endpoint for polling:

http

GET https://api.cheapaiapi.com/v1/task/{task_id}

Completed Task Example

json

{
  "id": "uuid_task_id",
  "status": "done",
  "credit_cost": 1,
  "metadata": {
    "json_url": "https://example.com/transcript.json",
    "srt_url": "https://example.com/transcript.srt"
  },
  "type": "speech_to_text"
}

What To Show Users

Original file name and upload size before submit
Immediate task state after upload instead of waiting synchronously
Separate download actions for JSON and SRT once done
Webhook status if your backend receives transcripts automatically