Pricing
Get started
Get started
Sales enablement

Accurate, multilingual transcription for sales calls

Power your platform with real-time or async speech-to-text and analysis, designed to scale and support global sales teams.

Trusted by 600+ AI assistants and contact center platforms

What you can build with Gladia

Enhanced LLM-based sales enablement features

Error-free transcripts, combined with Gladia’s proprietary key entity extraction algorithm, will enable you to extract the most relevant information from calls in seconds to enhance your CRM enrichment and note-taking capabilities.

Real-time assistance to sales reps

Integrate real-time suggestions and prompts, including battle cards, best responses, and coaching tips, based on the ongoing sales conversation.

Training and quality assurance

Build quality assurance systems to record sales calls and use AI to analyze them for script adherence, compliance with regulatory requirements, and sales reps' overall performance.

Automated customer support

Deploy custom conversational agents for round-the-clock support, capable of answering common questions and guiding customers through basic processes without the sales reps' direct involvement.

Our customers achieved

30%

less time spent on manual tasks

20+

languages transcribed per customer

75

%

instant user feature adoption

"Having tried numerous speech-to-text solutions, I can confidently say: Gladia's API outshines the rest. Their balance of accuracy, speed, and precise word timings is unparalleled."

Jean Patry

Co-founder

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