Example of using the API v1 for synchronous recognition
Written by
Updated at October 24, 2024
The example shows how the API v1 helps synchronously recognize speech in the OggOpus audio file format.
The example uses the following parameters:
- Language: Russian.
- Other parameters are left at their defaults.
Use the cURL utility to generate and send a request to the server for recognition.
The Yandex account or federated account are authenticated using an IAM token. If you use your service account, you do not need to include the folder ID in the request. Learn more about authentication in the SpeechKit API.
Sample request
POST request
cURL
Python 3
PHP
Send a request to convert speech to text:
POST /speech/v1/stt:recognize?topic=general&lang=ru-RU&folderId={<folder_ID>} HTTP/1.1
Host: stt.api.cloud.yandex.net
Authorization: Bearer <IAM_token>
... (binary content of an audio file)
Where:
topic: Language model.lang: Recognition language.folderId: Folder ID.<IAM_token>: IAM token.
Send a request to convert speech to text:
export FOLDER_ID=<folder_ID>
export IAM_TOKEN=<IAM_token>
curl \
--request POST \
--header "Authorization: Bearer ${IAM_TOKEN}" \
--data-binary "@speech.ogg" \
"https://stt.api.cloud.yandex.net/speech/v1/stt:recognize?topic=general&folderId=${FOLDER_ID}"
Where:
FOLDER_ID: Folder ID.IAM_TOKEN: IAM token.--data-binary: Name of the audio file for recognition.topic: Language model.
Send a request to convert speech to text:
import urllib.request
import json
FOLDER_ID = "<folder_ID>" # Folder ID
IAM_TOKEN = "<IAM_token>" # IAM token
with open("speech.ogg", "rb") as f:
data = f.read()
params = "&".join([
"topic=general",
"folderId=%s" % FOLDER_ID,
"lang=ru-RU"
])
url = urllib.request.Request("https://stt.api.cloud.yandex.net/speech/v1/stt:recognize?%s" % params, data=data)
# Authentication with an IAM token
url.add_header("Authorization", "Bearer %s" % IAM_TOKEN)
responseData = urllib.request.urlopen(url).read().decode('UTF-8')
decodedData = json.loads(responseData)
if decodedData.get("error_code") is None:
print(decodedData.get("result"))
Where:
FOLDER_ID: Folder ID.IAM_TOKEN: IAM token.speech.ogg: Name of the audio file for recognition.topic: Language model.lang: Recognition language.
Send a request to convert speech to text:
<?php
$token = '<IAM_token>'; # IAM token
$folderId = "<folder_ID>"; # Folder ID
$audioFileName = "speech.ogg";
$file = fopen($audioFileName, 'rb');
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, "https://stt.api.cloud.yandex.net/speech/v1/stt:recognize?lang=ru-RU&folderId=${folderId}&format=oggopus");
curl_setopt($ch, CURLOPT_HTTPHEADER, array('Authorization: Bearer ' . $token));
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
curl_setopt($ch, CURLOPT_BINARYTRANSFER, true);
curl_setopt($ch, CURLOPT_INFILE, $file);
curl_setopt($ch, CURLOPT_INFILESIZE, filesize($audioFileName));
$res = curl_exec($ch);
curl_close($ch);
$decodedResponse = json_decode($res, true);
if (isset($decodedResponse["result"])) {
echo $decodedResponse["result"];
} else {
echo "Error code: " . $decodedResponse["error_code"] . "\r\n";
echo "Error message: " . $decodedResponse["error_message"] . "\r\n";
}
fclose($file);
Where:
token: IAM token.folderId: Folder ID.audioFileName: Name of the audio file for recognition.lang: Recognition language.format: Format of the submitted audio file.
Response example
HTTP/1.1 200 OK
YaCloud-Billing-Units: 15
{
"result": "your number is 212-85-06"
}