API reference

Transcribe audio to text

POST /v1/audio/transcriptions request, response, and error contract.

View Markdown

POST /v1/audio/transcriptions

Transcribes audio to text using speech-to-text models. Accepts audio files via multipart form upload. Available models: openai/whisper-large-v3, openai/whisper-large-v3-turbo

Authentication¶

Send Authorization: Bearer $KOSCOMPUTE_API_KEY.

Request¶

Content type: multipart/form-data

Field	Type	Required	Description
`file`	string (binary)	Yes	Audio file (multipart)
`model`	string	Yes	See the endpoint guide for behavior and model support.
`language`	string	No	See the endpoint guide for behavior and model support.
`response_format`	string	No	Values: `json`, `text`, `srt`, `verbose_json`, `vtt`.
`temperature`	number	No	See the endpoint guide for behavior and model support.
`timestamp_granularities`	array	No	See the endpoint guide for behavior and model support.

Examples¶

cURL¶

curl https://api.koscompute.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $KOSCOMPUTE_API_KEY" \
  -F "file=@sample.wav" \
  -F "model=openai/whisper-large-v3-turbo"

Python¶

import os
import requests

with open("sample.wav", "rb") as audio:
    response = requests.post(
        "https://api.koscompute.com/v1/audio/transcriptions",
        headers={"Authorization": f"Bearer {os.environ['KOSCOMPUTE_API_KEY']}"},
        files={"file": ("sample.wav", audio, "audio/wav")},
        data={"model": "openai/whisper-large-v3-turbo"},
    )

JavaScript¶

const form = new FormData();
form.append("file", fileInput.files[0]);
form.append("model", "openai/whisper-large-v3-turbo");
const response = await fetch("https://api.koscompute.com/v1/audio/transcriptions", {
  method: "POST",
  headers: { Authorization: `Bearer ${process.env.KOSCOMPUTE_API_KEY}` },
  body: form,
});

Responses¶

Status	Meaning
`200`	Transcription result
`400`	Bad request — invalid parameters or payload
`401`	Invalid or missing API key
`403`	Model not allowed for this API key
`404`	Public model not found
`413`	Request body exceeds the limit
`429`	Rate limit or admission capacity is full. The message states when to retry; vision saturation also reports active/total vision concurrency.
`502`	Invalid or failed upstream response
`503`	No healthy route
`504`	Backend generation timeout
`500`	Internal server error

Next steps¶

Use the endpoint guide for complete workflows, model capability notes, streaming behavior, and retry advice.