Pricing
Get started
Get started
Media

Build cutting-edge media tools with AI transcription

Give your platform an edge with highly precise, multilingual transcription and AI-powered insights.

Trusted by 600+ AI assistants and contact center platforms

What you can build with Gladia

AI-powered video editing

AI transcription can remove silences, filler words and repetition to streamline the video editing process.

Automatic subtitles in 100+ languages

Accurately capture speech in non-English languages, including diverse accents.

Extract metadata from videos

You can use transcripts from videos to analyze the content of the video to generate automatic titles and more.

Our customers achieved

30%

less time spent on manual tasks

20+

languages transcribed per customer

75

%

instant user feature adoption

"We are 100% benchmark and evaluation driven. Gladia was one of the best providers selected on merit to transcribe user videos, especially for non-English languages. Their reactive customer support and data compliance make their offer really compelling."

Kojo Hinson

Group Engineering Manager

Built for developers

Add cutting-edge AI to your product in 3 clicks. Our API is compatible with all tech stacks and doesn’t require any AI expertise or setup costs.

async function makeFetchRequest(url: string, options: any) {
  const response = await fetch(url, options);
  return response.json();
}

async function pollForResult(resultUrl: string, headers: any) {
  while (true) {
    console.log("Polling for results...");
    const pollResponse = await makeFetchRequest(resultUrl, { headers });

    if (pollResponse.status === "done") {
      console.log("- Transcription done: \n ");
      console.log(pollResponse.result.transcription.full_transcript);
      break;
    } else {
      console.log("Transcription status : ", pollResponse.status);
      await new Promise((resolve) => setTimeout(resolve, 1000));
    }
  }
}

async function startTranscription() {
  const gladiaKey = "YOUR_GLADIA_API_TOKEN";
  const requestData = {
    audio_url:
      "YOUR_AUDIO_URL",
  };
  const gladiaUrl = "https://api.gladia.io/v2/transcription/";
  const headers = {
    "x-gladia-key": gladiaKey,
    "Content-Type": "application/json",
  };

  console.log("- Sending initial request to Gladia API...");
  const initialResponse = await makeFetchRequest(gladiaUrl, {
    method: "POST",
    headers,
    body: JSON.stringify(requestData),
  });

  console.log("Initial response with Transcription ID :", initialResponse);

  if (initialResponse.result_url) {
    await pollForResult(initialResponse.result_url, headers);
  }
}

startTranscription();
import requests
import time

def make_fetch_request(url, headers, method='GET', data=None):
    if method == 'POST':
        response = requests.post(url, headers=headers, json=data)
    else:
        response = requests.get(url, headers=headers)
    return response.json()

gladia_key = "YOUR_GLADIA_API_TOKEN"
request_data = {"audio_url": "YOUR_AUDIO_URL"}
gladia_url = "https://api.gladia.io/v2/transcription/"

headers = {
    "x-gladia-key": gladia_key,
    "Content-Type": "application/json"
}

print("- Sending initial request to Gladia API...")
initial_response = make_fetch_request(gladia_url, headers, 'POST', request_data)

print("Initial response with Transcription ID:", initial_response)
result_url = initial_response.get("result_url")

if result_url:
    while True:
        print("Polling for results...")
        poll_response = make_fetch_request(result_url, headers)
        
        if poll_response.get("status") == "done":
            print("- Transcription done: \n")
            print(poll_response.get("result", {}).get("transcription", {}).get("full_transcript"))
            break
        else:
            print("Transcription status:", poll_response.get("status"))
        time.sleep(1)
ss Lower AI infrastructure costs. We leverage a proprietary know-how to fit more AI on less hardware — without compromising on quality and performance.
ss Technical edge. With Gladia, you get access to an optimized version of the most sophisticated ASR models and regular software upgrades at no extra cost.
ss Reduced time-to-market. By embedding advanced AI into your applications directly, your users can derive full value from your product from day one.
ss Easy-to-scale. Increase your processing capacity easily with our pay-as-you go system. Our enterprise-grade API is built to adapt to your ever-growing needs.

Read more