Audio/Video Transcription

Transcribe audio or video to text

curl --request POST \
  --url https://api.deapi.ai/api/v2/audio/transcriptions \
  --header 'Accept: <accept>' \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form 'source_url=https://www.youtube.com/watch?v=jNQXAC9IVRw' \
  --form model=WhisperLargeV3 \
  --form 'source_file=<string>' \
  --form include_ts=false \
  --form ts_level=word \
  --form diarize=false \
  --form lang=en \
  --form include_metadata=false \
  --form return_result_in_response=false \
  --form webhook_url=https://your-server.com/webhooks/deapi \
  --form webhook_secret=a1b2c3d4e5f60708091a2b3c4d5e6f7081920a1b2c3d4e5f60708091a2b3c4d5 \
  --form 0.source_file='@example-file' \
  --form 1.source_file='@example-file'

import requests

url = "https://api.deapi.ai/api/v2/audio/transcriptions"

files = {
    "0.source_file": ("example-file", open("example-file", "rb")),
    "1.source_file": ("example-file", open("example-file", "rb"))
}
payload = {
    "source_url": "https://www.youtube.com/watch?v=jNQXAC9IVRw",
    "model": "WhisperLargeV3",
    "source_file": "<string>",
    "include_ts": "false",
    "ts_level": "word",
    "diarize": "false",
    "lang": "en",
    "include_metadata": "false",
    "return_result_in_response": "false",
    "webhook_url": "https://your-server.com/webhooks/deapi",
    "webhook_secret": "a1b2c3d4e5f60708091a2b3c4d5e6f7081920a1b2c3d4e5f60708091a2b3c4d5"
}
headers = {
    "Accept": "<accept>",
    "Authorization": "Bearer <token>"
}

response = requests.post(url, data=payload, files=files, headers=headers)

print(response.text)

const form = new FormData();
form.append('source_url', 'https://www.youtube.com/watch?v=jNQXAC9IVRw');
form.append('model', 'WhisperLargeV3');
form.append('source_file', '<string>');
form.append('include_ts', 'false');
form.append('ts_level', 'word');
form.append('diarize', 'false');
form.append('lang', 'en');
form.append('include_metadata', 'false');
form.append('return_result_in_response', 'false');
form.append('webhook_url', 'https://your-server.com/webhooks/deapi');
form.append('webhook_secret', 'a1b2c3d4e5f60708091a2b3c4d5e6f7081920a1b2c3d4e5f60708091a2b3c4d5');
form.append('0.source_file', '{
  "fileName": "example-file"
}');
form.append('1.source_file', '{
  "fileName": "example-file"
}');

const options = {method: 'POST', headers: {Accept: '<accept>', Authorization: 'Bearer <token>'}};

options.body = form;

fetch('https://api.deapi.ai/api/v2/audio/transcriptions', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.deapi.ai/api/v2/audio/transcriptions",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"source_url\"\r\n\r\nhttps://www.youtube.com/watch?v=jNQXAC9IVRw\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nWhisperLargeV3\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"source_file\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"include_ts\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"ts_level\"\r\n\r\nword\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"lang\"\r\n\r\nen\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"include_metadata\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"return_result_in_response\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_url\"\r\n\r\nhttps://your-server.com/webhooks/deapi\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_secret\"\r\n\r\na1b2c3d4e5f60708091a2b3c4d5e6f7081920a1b2c3d4e5f60708091a2b3c4d5\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"0.source_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n{\r\n  \"fileName\": \"example-file\"\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"1.source_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n{\r\n  \"fileName\": \"example-file\"\r\n}\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Accept: <accept>",
    "Authorization: Bearer <token>",
    "Content-Type: multipart/form-data"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.deapi.ai/api/v2/audio/transcriptions"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"source_url\"\r\n\r\nhttps://www.youtube.com/watch?v=jNQXAC9IVRw\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nWhisperLargeV3\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"source_file\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"include_ts\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"ts_level\"\r\n\r\nword\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"lang\"\r\n\r\nen\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"include_metadata\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"return_result_in_response\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_url\"\r\n\r\nhttps://your-server.com/webhooks/deapi\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_secret\"\r\n\r\na1b2c3d4e5f60708091a2b3c4d5e6f7081920a1b2c3d4e5f60708091a2b3c4d5\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"0.source_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n{\r\n  \"fileName\": \"example-file\"\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"1.source_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n{\r\n  \"fileName\": \"example-file\"\r\n}\r\n-----011000010111000001101001--")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Accept", "<accept>")
	req.Header.Add("Authorization", "Bearer <token>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.deapi.ai/api/v2/audio/transcriptions")
  .header("Accept", "<accept>")
  .header("Authorization", "Bearer <token>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"source_url\"\r\n\r\nhttps://www.youtube.com/watch?v=jNQXAC9IVRw\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nWhisperLargeV3\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"source_file\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"include_ts\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"ts_level\"\r\n\r\nword\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"lang\"\r\n\r\nen\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"include_metadata\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"return_result_in_response\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_url\"\r\n\r\nhttps://your-server.com/webhooks/deapi\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_secret\"\r\n\r\na1b2c3d4e5f60708091a2b3c4d5e6f7081920a1b2c3d4e5f60708091a2b3c4d5\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"0.source_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n{\r\n  \"fileName\": \"example-file\"\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"1.source_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n{\r\n  \"fileName\": \"example-file\"\r\n}\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.deapi.ai/api/v2/audio/transcriptions")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Accept"] = '<accept>'
request["Authorization"] = 'Bearer <token>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"source_url\"\r\n\r\nhttps://www.youtube.com/watch?v=jNQXAC9IVRw\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nWhisperLargeV3\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"source_file\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"include_ts\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"ts_level\"\r\n\r\nword\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"lang\"\r\n\r\nen\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"include_metadata\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"return_result_in_response\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_url\"\r\n\r\nhttps://your-server.com/webhooks/deapi\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_secret\"\r\n\r\na1b2c3d4e5f60708091a2b3c4d5e6f7081920a1b2c3d4e5f60708091a2b3c4d5\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"0.source_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n{\r\n  \"fileName\": \"example-file\"\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"1.source_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n{\r\n  \"fileName\": \"example-file\"\r\n}\r\n-----011000010111000001101001--"

response = http.request(request)
puts response.read_body

{
  "data": {
    "request_id": "c08a339c-73e5-4d67-a4d5-231302fbff9a"
  }
}

{
  "data": {},
  "message": "<string>",
  "errors": [
    "<unknown>"
  ],
  "statusCode": 123
}

{
  "message": "Client account is suspended. If you believe this is a mistake, contact us."
}

{
  "message": "The selected model does not support Text To Image.",
  "errors": {
    "model": [
      "This model is not available on your plan. Please upgrade to access it."
    ]
  }
}

{
  "message": "Too Many Attempts."
}

POST

api

audio

transcriptions

Transcribe audio or video to text

curl --request POST \
  --url https://api.deapi.ai/api/v2/audio/transcriptions \
  --header 'Accept: <accept>' \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form 'source_url=https://www.youtube.com/watch?v=jNQXAC9IVRw' \
  --form model=WhisperLargeV3 \
  --form 'source_file=<string>' \
  --form include_ts=false \
  --form ts_level=word \
  --form diarize=false \
  --form lang=en \
  --form include_metadata=false \
  --form return_result_in_response=false \
  --form webhook_url=https://your-server.com/webhooks/deapi \
  --form webhook_secret=a1b2c3d4e5f60708091a2b3c4d5e6f7081920a1b2c3d4e5f60708091a2b3c4d5 \
  --form 0.source_file='@example-file' \
  --form 1.source_file='@example-file'

import requests

url = "https://api.deapi.ai/api/v2/audio/transcriptions"

files = {
    "0.source_file": ("example-file", open("example-file", "rb")),
    "1.source_file": ("example-file", open("example-file", "rb"))
}
payload = {
    "source_url": "https://www.youtube.com/watch?v=jNQXAC9IVRw",
    "model": "WhisperLargeV3",
    "source_file": "<string>",
    "include_ts": "false",
    "ts_level": "word",
    "diarize": "false",
    "lang": "en",
    "include_metadata": "false",
    "return_result_in_response": "false",
    "webhook_url": "https://your-server.com/webhooks/deapi",
    "webhook_secret": "a1b2c3d4e5f60708091a2b3c4d5e6f7081920a1b2c3d4e5f60708091a2b3c4d5"
}
headers = {
    "Accept": "<accept>",
    "Authorization": "Bearer <token>"
}

response = requests.post(url, data=payload, files=files, headers=headers)

print(response.text)

const form = new FormData();
form.append('source_url', 'https://www.youtube.com/watch?v=jNQXAC9IVRw');
form.append('model', 'WhisperLargeV3');
form.append('source_file', '<string>');
form.append('include_ts', 'false');
form.append('ts_level', 'word');
form.append('diarize', 'false');
form.append('lang', 'en');
form.append('include_metadata', 'false');
form.append('return_result_in_response', 'false');
form.append('webhook_url', 'https://your-server.com/webhooks/deapi');
form.append('webhook_secret', 'a1b2c3d4e5f60708091a2b3c4d5e6f7081920a1b2c3d4e5f60708091a2b3c4d5');
form.append('0.source_file', '{
  "fileName": "example-file"
}');
form.append('1.source_file', '{
  "fileName": "example-file"
}');

const options = {method: 'POST', headers: {Accept: '<accept>', Authorization: 'Bearer <token>'}};

options.body = form;

fetch('https://api.deapi.ai/api/v2/audio/transcriptions', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.deapi.ai/api/v2/audio/transcriptions",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"source_url\"\r\n\r\nhttps://www.youtube.com/watch?v=jNQXAC9IVRw\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nWhisperLargeV3\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"source_file\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"include_ts\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"ts_level\"\r\n\r\nword\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"lang\"\r\n\r\nen\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"include_metadata\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"return_result_in_response\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_url\"\r\n\r\nhttps://your-server.com/webhooks/deapi\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_secret\"\r\n\r\na1b2c3d4e5f60708091a2b3c4d5e6f7081920a1b2c3d4e5f60708091a2b3c4d5\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"0.source_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n{\r\n  \"fileName\": \"example-file\"\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"1.source_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n{\r\n  \"fileName\": \"example-file\"\r\n}\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Accept: <accept>",
    "Authorization: Bearer <token>",
    "Content-Type: multipart/form-data"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.deapi.ai/api/v2/audio/transcriptions"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"source_url\"\r\n\r\nhttps://www.youtube.com/watch?v=jNQXAC9IVRw\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nWhisperLargeV3\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"source_file\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"include_ts\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"ts_level\"\r\n\r\nword\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"lang\"\r\n\r\nen\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"include_metadata\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"return_result_in_response\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_url\"\r\n\r\nhttps://your-server.com/webhooks/deapi\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_secret\"\r\n\r\na1b2c3d4e5f60708091a2b3c4d5e6f7081920a1b2c3d4e5f60708091a2b3c4d5\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"0.source_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n{\r\n  \"fileName\": \"example-file\"\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"1.source_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n{\r\n  \"fileName\": \"example-file\"\r\n}\r\n-----011000010111000001101001--")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Accept", "<accept>")
	req.Header.Add("Authorization", "Bearer <token>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.deapi.ai/api/v2/audio/transcriptions")
  .header("Accept", "<accept>")
  .header("Authorization", "Bearer <token>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"source_url\"\r\n\r\nhttps://www.youtube.com/watch?v=jNQXAC9IVRw\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nWhisperLargeV3\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"source_file\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"include_ts\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"ts_level\"\r\n\r\nword\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"lang\"\r\n\r\nen\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"include_metadata\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"return_result_in_response\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_url\"\r\n\r\nhttps://your-server.com/webhooks/deapi\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_secret\"\r\n\r\na1b2c3d4e5f60708091a2b3c4d5e6f7081920a1b2c3d4e5f60708091a2b3c4d5\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"0.source_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n{\r\n  \"fileName\": \"example-file\"\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"1.source_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n{\r\n  \"fileName\": \"example-file\"\r\n}\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.deapi.ai/api/v2/audio/transcriptions")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Accept"] = '<accept>'
request["Authorization"] = 'Bearer <token>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"source_url\"\r\n\r\nhttps://www.youtube.com/watch?v=jNQXAC9IVRw\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nWhisperLargeV3\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"source_file\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"include_ts\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"ts_level\"\r\n\r\nword\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"lang\"\r\n\r\nen\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"include_metadata\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"return_result_in_response\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_url\"\r\n\r\nhttps://your-server.com/webhooks/deapi\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_secret\"\r\n\r\na1b2c3d4e5f60708091a2b3c4d5e6f7081920a1b2c3d4e5f60708091a2b3c4d5\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"0.source_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n{\r\n  \"fileName\": \"example-file\"\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"1.source_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n{\r\n  \"fileName\": \"example-file\"\r\n}\r\n-----011000010111000001101001--"

response = http.request(request)
puts response.read_body

{
  "data": {
    "request_id": "c08a339c-73e5-4d67-a4d5-231302fbff9a"
  }
}

{
  "data": {},
  "message": "<string>",
  "errors": [
    "<unknown>"
  ],
  "statusCode": 123
}

{
  "message": "Client account is suspended. If you believe this is a mistake, contact us."
}

{
  "message": "The selected model does not support Text To Image.",
  "errors": {
    "model": [
      "This model is not available on your plan. Please upgrade to access it."
    ]
  }
}

{
  "message": "Too Many Attempts."
}

Unified transcription endpoint that replaces the five v1 endpoints (vid2txt, aud2txt, videofile2txt, audiofile2txt, transcribe). Accepts URLs or multipart file uploads. Returns a request_id for status polling.

Source detection is automatic: pass a public URL in source_url (audio and video both use this one field), or upload a file via multipart source_file. There are no video_url / audio_url fields.

Prerequisite: Consult the Model Selection endpoint to identify a valid model slug and check supported languages.

OpenAI SDK users: This endpoint is also available via the OpenAI-compatible surface as POST /v1/audio/transcriptions at https://oai.deapi.ai/v1. Maximum file size per upload is 20 MB for audio and 50 MB for video, subject to a global 75 MB request body cap. See OpenAI Compatibility and Limits & Quotas.

WhisperLargeV3 supports segment timestamps only and does not support diarization. WhisperLargeV3Ct2 adds word-level timestamps, per-segment confidence scores and speaker labels — and is the only model that accepts TikTok sources.

TikTok requires WhisperLargeV3Ct2. A TikTok source_url submitted with any other model — WhisperLargeV3 included — is rejected with 422 before the job is queued, and nothing is charged. Every other source (YouTube, X, Twitch, Kick, X/Twitter Spaces and uploaded files) runs on both models. The same pairing applies to quotes: platform: "tiktok" on /price is only valid with WhisperLargeV3Ct2.

Segment timestamps are free. include_ts: true with the default ts_level: "segment" costs exactly the same as a plain transcription — on every model, WhisperLargeV3Ct2 included. Only finer granularity is billed: on WhisperLargeV3Ct2, ts_level: "word" — and diarize, which carries the surcharge at any granularity, segment included — multiplies the duration-based price by 1.5. See Pricing.

Granularity is validated against the model. The levels a model accepts are published as info.limits.timestamp_levels by GET /api/v2/models. WhisperLargeV3 publishes ["segment"] and supports_diarization: false, so ts_level: "word" is rejected with 422 and an errors.ts_level entry, and diarize: true is rejected with 422 and an errors.diarize entry. WhisperLargeV3Ct2 publishes ["segment", "word"]. Read the model’s advertised levels before sending anything other than segment. See Errors.

A source with no speech returns an empty result, not an error. If the video or audio carries no recognisable words — silence, music only, ambient noise — the job still completes with status: "done" and the transcript comes back empty: no segments, no words, no speakers. Treat an empty transcript as a valid outcome and branch on it explicitly, rather than assuming the job failed. A job that genuinely failed reports status: "error" with an error_reason instead.

Source metadata

Set include_metadata: true to have the job-status response carry a metadata object describing the source — title, channel, uploader, upload date and engagement counts.

Metadata is a paid add-on: 0.005 USD per request. It is charged only on sources that can actually return it, so an uploaded file — which has no source to describe — returns null and is never charged. See Pricing.

Only URL sources have metadata, and how much you get depends on the platform. The field names are the same either way, and anything a platform does not expose comes back as null rather than being omitted.

Metadata	TikTok	YouTube
`id`, `title`, `description`, `channel`	✅	✅
`duration_seconds`, `extractor`	✅	✅
`view_count`, `like_count`	✅	✅
`comment_count`	✅	❌
`repost_count`, `save_count`	✅	❌
`uploader`, `uploader_url`	✅	❌
`channel_id`, `channel_url`	✅	❌
`webpage_url`	✅	❌
`timestamp`, `upload_date`	✅	❌
`thumbnails[]`	✅	❌
`fulltitle`, `has_audio`, `is_live`	✅	❌
`tags`, `categories`, `chapters`, `heatmap`, `availability`, `channel_follower_count`	✅*	❌

* Present in the response schema, but may come back null depending on the individual TikTok video.

Authorizations

Authorization

string

header

required

Sanctum personal access token, sent as Authorization: Bearer <token>. The token is opaque — it carries no claims and no embedded expiry, so do not attempt to decode it. Issue and revoke tokens from your account dashboard.

Headers

enum<string>

default:application/json

required

Available options:

application/json

Body

multipart/form-data

Transcription parameters. Provide exactly one of source_url or source_file.

From a source URL
From an uploaded file

A source is MANDATORY and comes in exactly one of two shapes — source_url for a hosted video/audio, or source_file for an upload. Sending neither is a 422, and sending both is a 422 as well; the oneOf below is that choice, not a pair of optional fields. Everything else applies to both. The /price twin of this endpoint accepts a third shape, duration_seconds, which this one does not.

source_url

string

required

URL of video/audio to transcribe (YouTube, Twitter/X, Twitch, Kick, TikTok, Twitter Spaces). Mutually exclusive with source_file.

Example:

"https://www.youtube.com/watch?v=jNQXAC9IVRw"

model

string

required

The model to use for transcription. Available models can be retrieved via the GET /api/v2/models endpoint.

Example:

"WhisperLargeV3"

source_file

file

Audio or video file to transcribe. Supported audio: aac, mpeg, ogg, wav, webm, flac. Supported video: mp4, mpeg, quicktime, avi, wmv, ogg. Mutually exclusive with source_url.

include_ts

boolean | null

default:false

Should transcription include timestamps. Implied when diarize is true. Segment-level timestamps are included in the base price — see ts_level.

Example:

false

ts_level

enum<string> | null

default:segment

Timestamp granularity. Only applies when include_ts is true, otherwise ignored. Granularity affects the price on models that price timestamps separately: segment is included in the base price, while word and char carry a surcharge. The levels a model offers are published as info.limits.timestamp_levels by GET /api/v2/models; requesting an unsupported level is rejected.

Available options:

segment,

word,

char,

null

Example:

"word"

diarize

boolean | null

default:false

Label each timed unit with a detected speaker. Requires a model whose info.features.supports_diarization is true, and implies include_ts. Carries the timestamp surcharge at ANY granularity, including segment.

Example:

false

lang

string | null

Language hint for the transcription, e.g. en or pl. Region subtags are stripped (en-us becomes en), and auto means auto-detect. Omit to auto-detect. When a model publishes info.limits.languages via GET /api/v2/models, requesting a language outside that list is rejected; a model publishing no such list accepts any value.

Maximum string length: 16

Example:

"en"

include_metadata

boolean | null

default:false

If true, the job-status response carries a metadata object describing the source — title, channel, uploader, upload date and engagement counts such as views, likes and comments. Only URL sources have any; an uploaded file returns null. YouTube resolves through the official Data API and returns a smaller block — id, title, channel, description, duration_seconds, extractor, view_count, like_count — because that API has no equivalent for the rest; the field names match the other platforms. Fields absent on a platform are null rather than omitted. On models that price metadata this carries a flat surcharge, charged only on sources that can return it — an upload, which has no source to describe, is never charged for the flag.

Example:

false

return_result_in_response

boolean | null

default:false

If true, the result will be returned directly in the response instead of only download url.

Example:

false

webhook_url

string<uri> | null

Optional HTTPS URL to receive webhook notifications for job status changes (processing, completed, failed). Must be HTTPS. Max 2048 characters. A per-request URL is self-contained: it is delivered even when the account has no webhook configuration, or the account webhook is disabled. See the webhooks block at the top level of this document for the event payloads and the headers each delivery carries.

Maximum string length: 2048

Example:

"https://your-server.com/webhooks/deapi"

webhook_secret

string | null

Optional per-request HMAC secret (min. 32 chars) used to sign the webhook callback. Overrides the account-default secret for this job only. If omitted, the account-default secret signs the callback; if no secret exists at all, the callback is still delivered but UNSIGNED (empty X-DeAPI-Signature header). Requires webhook_url to also be set.

Required string length: 32 - 255

Example:

"a1b2c3d4e5f60708091a2b3c4d5e6f7081920a1b2c3d4e5f60708091a2b3c4d5"

Response

ID of the inference request.

data

object

required

Information from success endpoint

Show child attributes

Overview

Images

Videos

Audio

Embeddings

Prompt Enhancement

Utilities

Audio/Video Transcription

Source metadata

Authorizations

Headers

Body

Response

​Source metadata

Authorizations

Headers

Body

Response

Source metadata