Transcribe real-world audio with an API call.
Unlock conversational intelligence with transcription and context on the world’s best speech AI platform. Easy to integrate, simple to scale.
Transcribe real-world audio with an API call.
Unlock conversational intelligence with transcription and context on the world’s best speech AI platform. Easy to integrate, simple to scale.
Compare our pricing
$3,999 USD/year
Lorem ipsum dolor sit amet consectetur.
$6,500 USD/year
Lorem ipsum dolor sit amet consectetur.
$6,500 USD/year
Lorem ipsum dolor sit amet consectetur.
$6,500 USD/year
Lorem ipsum dolor sit amet consectetur.
Batch process (1hr of audio)
~8 seconds
~8 seconds
4980 seconds
4980 seconds
Real-time steaming lag
<300ms
Not available
Not available
Tailored speech models
Deep speech (search)
Batch process (1hr of audio)
~8 seconds
~8 seconds
4980 seconds
4980 seconds
Deep speech (search)
Not available
Noise Reduction
This is a headline to describe the features.
Unlock conversational intelligence with transcription and context on the world’s best speech AI platform. Easy to integrate, simple to scale.
1const url = 'https://your-api-endpoint.com/data';
2const data = {
3 key1: 'value1',
4 key2: 'value2'
5};
6
7fetch(url, {
8 method: 'POST',
9 headers: {
10 'Content-Type': 'application/json'
11 },
12 body: JSON.stringify(data)
13})
14.then(response => response.json())
15.then(data => {
16 console.log(data);
17})
18.catch((error) => {
19 console.error('Error:', error);
20});
1import requests
2import json
3
4url = 'https://your-api-endpoint.com/data'
5data = {
6 'key1': 'value1',
7 'key2': 'value2'
8}
9
10headers = {
11 'Content-Type': 'application/json'
12}
13
14response = requests.post(url, headers=headers, data=json.dumps(data))
15
16if response.status_code == 200:
17 print(response.json())
18else:
19 print("Error:", response.status_code)
20
1using System;
2using System.Net.Http;
3using System.Text;
4using System.Threading.Tasks;
5using Newtonsoft.Json;
6
7public class Program
8{
9 private static readonly HttpClient client = new HttpClient();
10
11 public static async Task Main(string[] args)
12 {
13 var url = "https://your-api-endpoint.com/data";
14 var data = new
15 {
16 key1 = "value1",
17 key2 = "value2"
18 };
19
20 var jsonString = JsonConvert.SerializeObject(data); // Using Newtonsoft.Json to serialize the object to JSON string
21 var content = new StringContent(jsonString, Encoding.UTF8, "application/json");
22
23 HttpResponseMessage response = await client.PostAsync(url, content);
24
25 if (response.IsSuccessStatusCode)
26 {
27 string responseBody = await response.Content.ReadAsStringAsync();
28 Console.WriteLine(responseBody);
29 }
30 else
31 {
32 Console.WriteLine($"Error: {response.StatusCode}");
33 }
34 }
35}
36
1<?php
2
3$url = "https://your-api-endpoint.com/data";
4$data = array(
5 'key1' => 'value1',
6 'key2' => 'value2'
7);
8
9// Initialize cURL session
10$ch = curl_init($url);
11
12// Set cURL options
13curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
14curl_setopt($ch, CURLOPT_POST, true);
15curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($data));
16curl_setopt($ch, CURLOPT_HTTPHEADER, array(
17 'Content-Type: application/json'
18));
19
20// Execute cURL session and get the response
21$response = curl_exec($ch);
22
23// Check for errors
24if (!$response) {
25 die('Error: "' . curl_error($ch) . '" - Code: ' . curl_errno($ch));
26}
27
28// Close cURL session
29curl_close($ch);
30
31// Print the response
32echo $response;
33
34?>
1require 'net/http'
2require 'json'
3require 'uri'
4
5url = URI.parse("https://your-api-endpoint.com/data")
6data = {
7 'key1' => 'value1',
8 'key2' => 'value2'
9}
10
11http = Net::HTTP.new(url.host, url.port)
12http.use_ssl = true if url.scheme == 'https'
13
14request = Net::HTTP::Post.new(url.path, {
15 'Content-Type' => 'application/json'
16})
17
18request.body = data.to_json
19
20response = http.request(request)
21
22if response.is_a?(Net::HTTPSuccess)
23 puts response.body
24else
25 puts "Error: #{response.code}"
26end
1curl -X POST "https://your-api-endpoint.com/data" \
2 -H "Content-Type: application/json" \
3 -d '{
4 "key1": "value1",
5 "key2": "value2"
6 }'
Maximum flexibility
We provide flexible deployment options, robust features and multilingual support, and fit-for-purpose DSLMs easily adapted to your customers' unique needs.
20X faster
Transcribe in real-time or an hour of pre-recorded audio in about 12 seconds.
Blanket feature. Lead the industry with the most accurate models in the market.
Some more text.
Blanket feature. Lead the industry with the most accurate models in the market.
Blanket feature. Lead the industry with the most accurate models in the market.
Blanket feature. Lead the industry with the most accurate models in the market.
Blanket feature. Lead the industry with the most accurate models in the market.
Blanket feature. Lead the industry with the most accurate models in the market.
Trusted by the world’s top
, , &We’re on a mission to become the human language company.
Lorem ipsum dolor sit amet consectetur. Sed nulla nulla proin dignissim sed.
Essential building blocks for language AI.
Deepgram is a foundational AI company providing the speech-to-text and language understanding capabilities you need to make your data readable and actionable by humans…or machines.
>90% accuracy
Deepgram leads the industry with most accurate models in market across use case categories.
3X lower cost
Optimized speech recognition and domain-specific language models are precisely tuned on our end-to-end GPU-based infrastructure to give superior, tailored performance at the lowest cost .
Maximum flexibility
We provide flexible deployment options, robust features and multilingual support, and fit-for-purpose DSLMs easily adapted to your customers' unique needs.
20X faster
Transcribe in real-time or an hour of pre-recorded audio in about 12 seconds.
Frequently Asked Questions
Absolutely. We’ll even give you free credits to try out our transcription as well as our formatting and understanding features. No credit card required.
Nova generally has higher accuracy and is also a cost-effective choice. Some languages are only supported in Enhanced and Base. See Model Overview.
Our Growth plan offers 20% savings for pre-paying for credits. If you’re looking to transcribe over 10,000 hours of audio per year, you can save even more with a Premium plan. Contact us for more information.
We support over 40 audio and video formats, documented here.
You can purchase credits upfront with a credit card. Credits will be deducted from your balance as you use our API. Pay As You Go credits never expire. Growth plan credits expire 1 year from purchase unless you renew or upgrade.
Definitely. In fact, we’ve got the fastest real-time transcription in the biz with latency times of under 300 milliseconds.
If you’re on the Growth plan and have saved a credit card, you can continue to use our API with a 10% overage fee billed at the start of each month.
We support over 30 languages and dialects for transcription (see list here) with over 100 supported for translation.
Credits purchased on a Growth plan expire a year from purchase unless you renew or upgrade.
Sure thing. You can get help from our community over at Github Discussions. If you are subscribed to our Premium plan, reach out to our support team via email for assistance.
We bill based on usage not users. Add as many team members and collaborators as you wish!
You sure can. Contact us about getting on a Premium plan to expand your deployment capabilities.
Language AI models to power your apps
Power your apps with world-class speech-to-text and domain-specific language models (DSLMs). Effortlessly accurate. Blazing fast. Enterprise-ready scale. Unbeatable pricing. Everything developers need to build with confidence and ship faster.
Try our speech-to-text & understanding API
Play around with transcribing sample audio files or our live streaming transcription demo. Explore how our audio understanding models work.
NASA: First All Female Space Walk
POST https://api.deepgram.com/v1/listen
1{
2 "url":"nasa_demo"
3}
Give it a try.
Transcription
Alright. I’m ready. Good evening. I’m Dr. Emmett Brown. I’m standing on the parking lot at Twin Pines Mall. It’s Saturday Morning October twenty sixth nineteen eighty five one eighteen AM. And this is temporal experiment number one. Come on Einey. Hey, boy. Get in there. At a boy. In you go. Sit down. Get your seatbelt on. That’s it. Okay. Please note, that Einstein’s clock is in precise synchronization with my control watch. Got it? Right. Check Doc. Good. Have a good trip Einstein. Watch your head. You got that thing hooked up to the car? Watch this. Yeah Ok. Not me the car, the car. If my calculations are correct. When this baby hits eighty eight miles per hour, you’re gonna see some serious s**t.
“summary”: “An experiment is being conducted. The speaker is Dr. Emmett Brown and he gives his location and the date and time. Someone is traveling by car and the experiment is about to begin.”
Watch this watch this. What did I tell you? Eighty eight miles per hour. The thermal displacement occurred exactly what? One O two AM and zero seconds. Jesus Christ. Jesus Christ, doc, you disintegrated Einstein. Calm down Marty. I didn’t disintegrate anything. The molecular structure of both Einstein and the car are completely intact. Then where hell are they? The appropriate question is, when the hell are they? You see, Einstein has just become the world’s first time traveler. I set him into the future. One minute into the future to be exact. Now precisely one twenty one AM and zero seconds we shall catch up with him and the time machine. Wait a minute. Wait a minute. Doc. Are you telling me that you built a time machine out of a Delorean?
“summary”: “There is concern over the traveler’s safety but everything is intact. The event is the world’s first time travel experiment made out of a Delorean.”
Try our speech-to-text & understanding API
Play around with transcribing sample audio files or our live streaming transcription demo. Explore how our audio understanding models work.
As we’ve begun to roll out Deepgram to our customers, we’ve noticed the platform’s distinct ability to quickly and accurately transcribe product and company names.