Speech to Text

Overview

The Speech-to-Text API transcribes an audio file to text in a single synchronous request. Upload audio, get back the transcript in the same response.


POST /api/stt/transcribe/

Billed per second of audio. Pairs with the Text to Speech endpoint.

Authentication

Send your key in the x-api-key header (browser sessions may use a JWT Authorization: Bearer <token> instead). See API Keys to create one.


x-api-key: sk_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

Transcribe audio


POST /api/stt/transcribe/

Send the audio as multipart/form-data.


curl -X POST https://api.oshara.ai/api/stt/transcribe/ \
  -H "x-api-key: $OSHARA_KEY" \
  -F "file=@recording.wav" \
  -F "model=whisper" \
  -F "language=en"

Request fields

Field	Type	Required	Description
`file`	file	✓	The audio file to transcribe. Max 50 MB.
`model`	string		`whisper` (default) or `omnilingual`. Any other value falls back to `whisper`.
`language`	string		`en` (default) or `ne` (Nepali).

Models

Model	Best for
`whisper`	General transcription; strong Nepali support (default).
`omnilingual`	Broad multilingual coverage (alias: `sherpa`).

Response

Returns JSON with the transcript:


{
  "success": true,
  "message": "Request successful",
  "data": {
    "transcript": "…transcribed text…",
    "model": "whisper",
    "language": "en"
  }
}

Billing

Charged per second of audio (rounded up, with a minimum). Duration is measured from the uploaded file.

Errors

Status	Meaning
`400`	No `file` provided, or the file exceeds the 50 MB limit.
`401`	Missing or invalid `x-api-key`.
`502`	Transcription failed upstream.


{ "success": false, "message": "An error occurred",
  "errors": { "error": "..." } }