Speech to Text — OneHub

Speech-to-text via OpenAI Whisper. Accepts multipart/form-data or JSON.

Docs

Docs Quick Start Authentication SDK Setup Available Models Rate Limits Chat Completions Streaming List Models Embeddings Image Generation Text to Speech Speech to Text Billing & Wallet Webhooks Errors

Speech to Text

POST https://www.onehub.design/v1/audio/transcriptions

Request (multipart)

curl https://www.onehub.design/v1/audio/transcriptions \
  -H "Authorization: Bearer sk-onehub-xxx" \
  -F "file=@/path/to/audio.mp3" \
  -F "model=whisper-1"

Response

{
  "text": "Hello from OneHub! This is a transcription of the audio."
}

Parameters

Field	Type	Description
`file`	file	Audio in `flac`, `mp3`, `mp4`, `mpeg`, `mpga`, `m4a`, `ogg`, `wav`, or `webm`
`model`	string	`whisper-1`
`language`	string	Optional ISO-639-1 language hint, e.g. `en`
`response_format`	string	`json`, `text`, `srt`, `verbose_json`, `vtt`