Speech to Text

Convert audio and video content into accurate text transcriptions.

Try it out

Test the Speech to Text API directly in your browser with our interactive playground.

Overview

The Speech to Text API accepts audio or video files and returns transcribed text. It supports multiple languages and provides high accuracy even with background noise.

API Reference

Endpoint

POST https://api.tryvinci.com/vincistt

Headers

Name	Type	Description
X-User-ID	string	Required. Your user ID

Request Body

Multipart form data with:

Parameter	Type	Description
file	File	Audio/video file to transcribe

Response

{
  text: string // Transcribed text
}

Code Examples

Python

import requests

url = "https://api.tryvinci.com/vincistt"
headers = {"X-User-ID": "your-user-id"}
files = {"file": open("video.mp4", "rb")}

response = requests.post(url, headers=headers, files=files)
print(response.json()["text"])

JavaScript

const formData = new FormData();
formData.append('file', videoFile);

const response = await fetch('https://api.tryvinci.com/vincistt', {
  method: 'POST',
  headers: {
    'X-User-ID': 'your-user-id',
  },
  body: formData,
});

const data = await response.json();
console.log(data.text);

Best Practices

File Format Support

Supported formats include MP3, WAV, MP4, and MOV. For best results, ensure good audio quality.

Language Detection

The API automatically detects the spoken language. No need to specify the language parameter.

Error Handling

Always implement proper error handling to manage rate limits and potential API errors.

Optimization

For large files, consider splitting them into smaller segments (30-60 seconds) for better performance.