OpenAI Whisper API - Speech-to-text transcription through UniterRouter. Convert audio to text with GPT-4 level accuracy, supports multiple languages and formats.

Audio

Transcribe audio files to text using state-of-the-art speech recognition models.

Endpoint

POST https://api.uniterouter.ai/v1/audio/transcriptions

Request

This endpoint accepts multipart/form-data with the following fields:

Field	Type	Required	Description
`file`	file	Yes	The audio file to transcribe
`model`	string	Yes	Model ID (e.g., `whisper-1`)
`language`	string	No	Language code (ISO 639-1)
`prompt`	string	No	Optional context to guide transcription
`response_format`	string	No	`json`, `text`, `srt`, `vtt`, `verbose_json`
`temperature`	number	No	Sampling temperature (0-1)

Supported Formats

Format	Extensions
MP3	`.mp3`
MP4	`.mp4`, `.m4a`
WAV	`.wav`
WebM	`.webm`
FLAC	`.flac`
OGG	`.ogg`

File Size Limit: Maximum file size is 25 MB. For larger files, split them into segments.

Supported Models

Model	Provider	Languages	Notes
`whisper-1`	OpenAI	50+	Best accuracy
`whisper-large-v3`	Groq	50+	Fast inference

Example Request

curl https://api.uniterouter.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $UNITEROUTER_API_KEY" \
  -F file="@audio.mp3" \
  -F model="whisper-1"

from openai import OpenAI

client = OpenAI(
    base_url="https://api.uniterouter.ai/v1",
    api_key="your_api_key",
)

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

print(response.text)

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

const client = new OpenAI({
  baseURL: "https://api.uniterouter.ai/v1",
  apiKey: process.env.UNITEROUTER_API_KEY,
});

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

console.log(response.text);

Response

JSON Format (default)

{
  "text": "Hello, this is a sample transcription of the audio file."
}

Verbose JSON Format

{
  "task": "transcribe",
  "language": "english",
  "duration": 12.5,
  "text": "Hello, this is a sample transcription.",
  "segments": [
    {
      "id": 0,
      "start": 0.0,
      "end": 2.5,
      "text": "Hello,"
    }
  ]
}

Language Support

Whisper supports 50+ languages. Specify language for better accuracy:

response = client.audio.transcriptions.create(
    model="whisper-1",
    file=audio_file,
    language="en"  # English
)

Common language codes: en, zh, ja, ko, es, fr, de

Audio

On this page