Skip to main content

Documentation Index

Fetch the complete documentation index at: https://runcrate.ai/docs/llms.txt

Use this file to discover all available pages before exploring further.

Transcribe audio files to text using ASR (Automatic Speech Recognition) models.

Endpoint

POST https://api.runcrate.ai/v1/audio/transcriptions

Basic Usage

curl https://api.runcrate.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer rc_live_YOUR_API_KEY" \
  -F model="openai/whisper-large-v3" \
  -F file=@audio.mp3

Parameters

ParameterTypeDescription
modelstringModel ID (required)
filefileAudio file (required). Sent as multipart form data.
Supported audio formats: MP3, WAV, M4A, FLAC, OGG, WebM.

Response

{
  "text": "Hello, welcome to Runcrate!",
  "duration": 2.5,
  "language": "en"
}
FieldTypeDescription
textstringThe transcribed text
durationnumberAudio duration in seconds
languagestringDetected language code