ELelectronhub

Create Transcription

Transcribe audio to text (OpenAI-compatible multipart upload). Max 25 MB / 25 minutes.

post/audio/transcriptions

Request

  • Base URL
    https://api.electronhub.ai/v1
  • URL
    https://api.electronhub.ai/v1/audio/transcriptions
  • Auth
    HTTP bearer

Request body multipart/form-data

filestring binary required

Audio file (flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm). Max 25 MB / 25 minutes.

modelstring required

STT model ID

languagestring

ISO-639-1 code, or auto/multi where supported

promptstring

Optional hint text (Whisper-family)

response_format'json' | 'text' | 'srt' | 'verbose_json' | 'vtt'
temperaturenumber
model_configstring

JSON string of engine-specific options (e.g. Deepgram)

smart_formatboolean
punctuateboolean
diarizeboolean
utteranceboolean
numeralsboolean

Example request

{
  "model": "deepgram-nova-3",
  "language": "auto"
}

Response

Transcription result

textstring required

Transcribed text

durationnumber

Audio duration in seconds (verbose_json)

Example response

{
  "text": "Hello, how are you?"
}

Changes

No recorded changes to this operation across all 2 revisions of this API.