Audio transcriptions

POST /v1/audio/transcriptions

Transcribes an audio file into text. The request body must be sent as multipart/form-data with the audio file included as a form field. This endpoint maps to the createTranscription operation and is compatible with the OpenAI Whisper API.

Request headers

string

The provider to route the request to (e.g. openai). Required when not using a config.

string

Your provider API key.

string

A JSON config object or config ID that defines routing, fallbacks, retries, and more.

string

A virtual key ID from Portkey Cloud.

Request body

This endpoint accepts multipart/form-data. The audio file must be uploaded as a file field named file.

file

required

The audio file to transcribe. Supported formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm. Maximum file size is 25 MB.

string

required

The speech-to-text model to use (e.g. whisper-1, gpt-4o-transcribe).

string

The language of the audio, in ISO-639-1 format (e.g. en, fr, de). Providing the language improves accuracy and latency.

string

Optional text to guide the model’s style or provide context. The prompt should match the language of the audio.

string

default:"json"

The format of the transcription output. One of json, text, srt, verbose_json, or vtt.

number

default:"0"

Sampling temperature between 0 and 1. Higher values produce more varied output. Set to 0 for deterministic transcription.

string[]

The granularity of timestamps to include. Requires response_format to be verbose_json. Accepts word and/or segment.

Response

The response format depends on the response_format parameter. json (default)

string

The transcribed text.

verbose_json

string

The full transcribed text.

string

The detected language of the audio.

number

The duration of the audio file in seconds.

object[]

Segment-level transcription data, present when timestamp_granularities includes segment.

Show properties

integer

Segment index.

number

Start time of the segment in seconds.

number

End time of the segment in seconds.

string

The transcribed text for this segment.

object[]

Word-level transcription data, present when timestamp_granularities includes word.

Show properties

string

The transcribed word.

number

Start time in seconds.

number

End time in seconds.

text, srt, vtt — Plain-text or subtitle format strings.

Code examples

curl http://localhost:8787/v1/audio/transcriptions \
  -H "x-portkey-provider: openai" \
  -H "x-portkey-api-key: $OPENAI_API_KEY" \
  -F "model=whisper-1" \
  -F "file=@audio.mp3" \
  -F "language=en" \
  -F "response_format=json"

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:8787/v1",
    api_key="$OPENAI_API_KEY",
    default_headers={
        "x-portkey-provider": "openai",
    },
)

with open("audio.mp3", "rb") as audio_file:
    response = client.audio.transcriptions.create(
        model="whisper-1",
        file=audio_file,
        language="en",
    )

print(response.text)

import OpenAI from "openai";
import fs from "fs";

const client = new OpenAI({
  baseURL: "http://localhost:8787/v1",
  apiKey: process.env.OPENAI_API_KEY,
  defaultHeaders: {
    "x-portkey-provider": "openai",
  },
});

const response = await client.audio.transcriptions.create({
  model: "whisper-1",
  file: fs.createReadStream("audio.mp3"),
  language: "en",
});

console.log(response.text);

Overview

Chat

Multimodal

Files & Batches

Other

POST /v1/audio/transcriptions

Request headers

Request body

Response

Code examples

​POST /v1/audio/transcriptions

​Request headers

​Request body

​Response

​Code examples

POST /v1/audio/transcriptions

Request headers

Request body

Response

Code examples