Transcribe audio

curl --request POST \
  --url https://ai.liara.ir/api/{workspaceID}/v1/audio/transcriptions \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "openai/whisper-1",
  "input_audio": {
    "data": "UklGRiQAAABXQVZFZm10IBAAAAABAAEA...",
    "format": "wav"
  },
  "language": "en",
  "response_format": "json",
  "temperature": 0,
  "timestamp_granularities": [
    "segment"
  ]
}
'

import requests

url = "https://ai.liara.ir/api/{workspaceID}/v1/audio/transcriptions"

payload = {
    "model": "openai/whisper-1",
    "input_audio": {
        "data": "UklGRiQAAABXQVZFZm10IBAAAAABAAEA...",
        "format": "wav"
    },
    "language": "en",
    "response_format": "json",
    "temperature": 0,
    "timestamp_granularities": ["segment"]
}
headers = {
    "Authorization": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'openai/whisper-1',
    input_audio: {data: 'UklGRiQAAABXQVZFZm10IBAAAAABAAEA...', format: 'wav'},
    language: 'en',
    response_format: 'json',
    temperature: 0,
    timestamp_granularities: ['segment']
  })
};

fetch('https://ai.liara.ir/api/{workspaceID}/v1/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://ai.liara.ir/api/{workspaceID}/v1/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 => json_encode([
    'model' => 'openai/whisper-1',
    'input_audio' => [
        'data' => 'UklGRiQAAABXQVZFZm10IBAAAAABAAEA...',
        'format' => 'wav'
    ],
    'language' => 'en',
    'response_format' => 'json',
    'temperature' => 0,
    'timestamp_granularities' => [
        'segment'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: <api-key>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($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://ai.liara.ir/api/{workspaceID}/v1/audio/transcriptions"

	payload := strings.NewReader("{\n  \"model\": \"openai/whisper-1\",\n  \"input_audio\": {\n    \"data\": \"UklGRiQAAABXQVZFZm10IBAAAAABAAEA...\",\n    \"format\": \"wav\"\n  },\n  \"language\": \"en\",\n  \"response_format\": \"json\",\n  \"temperature\": 0,\n  \"timestamp_granularities\": [\n    \"segment\"\n  ]\n}")

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

	req.Header.Add("Authorization", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

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

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

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://ai.liara.ir/api/{workspaceID}/v1/audio/transcriptions")
  .header("Authorization", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"openai/whisper-1\",\n  \"input_audio\": {\n    \"data\": \"UklGRiQAAABXQVZFZm10IBAAAAABAAEA...\",\n    \"format\": \"wav\"\n  },\n  \"language\": \"en\",\n  \"response_format\": \"json\",\n  \"temperature\": 0,\n  \"timestamp_granularities\": [\n    \"segment\"\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://ai.liara.ir/api/{workspaceID}/v1/audio/transcriptions")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"openai/whisper-1\",\n  \"input_audio\": {\n    \"data\": \"UklGRiQAAABXQVZFZm10IBAAAAABAAEA...\",\n    \"format\": \"wav\"\n  },\n  \"language\": \"en\",\n  \"response_format\": \"json\",\n  \"temperature\": 0,\n  \"timestamp_granularities\": [\n    \"segment\"\n  ]\n}"

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

{
  "text": "Hello, this is a transcription test."
}

Audio Transcriptions

Transcribe audio

Transcribes the provided audio using the specified speech-to-text model.

The API accepts audio in either JSON or multipart/form-data format.

For JSON requests, provide the audio as a Base64-encoded string through the input_audio.data field and specify the audio format through input_audio.format.

For multipart/form-data requests, upload the audio file using the file field.

The request is billed according to the selected speech-to-text model and the usage associated with the transcription request.

POST

api

{workspaceID}

audio

transcriptions

Transcribe audio

curl --request POST \
  --url https://ai.liara.ir/api/{workspaceID}/v1/audio/transcriptions \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "openai/whisper-1",
  "input_audio": {
    "data": "UklGRiQAAABXQVZFZm10IBAAAAABAAEA...",
    "format": "wav"
  },
  "language": "en",
  "response_format": "json",
  "temperature": 0,
  "timestamp_granularities": [
    "segment"
  ]
}
'

import requests

url = "https://ai.liara.ir/api/{workspaceID}/v1/audio/transcriptions"

payload = {
    "model": "openai/whisper-1",
    "input_audio": {
        "data": "UklGRiQAAABXQVZFZm10IBAAAAABAAEA...",
        "format": "wav"
    },
    "language": "en",
    "response_format": "json",
    "temperature": 0,
    "timestamp_granularities": ["segment"]
}
headers = {
    "Authorization": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'openai/whisper-1',
    input_audio: {data: 'UklGRiQAAABXQVZFZm10IBAAAAABAAEA...', format: 'wav'},
    language: 'en',
    response_format: 'json',
    temperature: 0,
    timestamp_granularities: ['segment']
  })
};

fetch('https://ai.liara.ir/api/{workspaceID}/v1/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://ai.liara.ir/api/{workspaceID}/v1/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 => json_encode([
    'model' => 'openai/whisper-1',
    'input_audio' => [
        'data' => 'UklGRiQAAABXQVZFZm10IBAAAAABAAEA...',
        'format' => 'wav'
    ],
    'language' => 'en',
    'response_format' => 'json',
    'temperature' => 0,
    'timestamp_granularities' => [
        'segment'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: <api-key>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($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://ai.liara.ir/api/{workspaceID}/v1/audio/transcriptions"

	payload := strings.NewReader("{\n  \"model\": \"openai/whisper-1\",\n  \"input_audio\": {\n    \"data\": \"UklGRiQAAABXQVZFZm10IBAAAAABAAEA...\",\n    \"format\": \"wav\"\n  },\n  \"language\": \"en\",\n  \"response_format\": \"json\",\n  \"temperature\": 0,\n  \"timestamp_granularities\": [\n    \"segment\"\n  ]\n}")

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

	req.Header.Add("Authorization", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

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

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

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://ai.liara.ir/api/{workspaceID}/v1/audio/transcriptions")
  .header("Authorization", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"openai/whisper-1\",\n  \"input_audio\": {\n    \"data\": \"UklGRiQAAABXQVZFZm10IBAAAAABAAEA...\",\n    \"format\": \"wav\"\n  },\n  \"language\": \"en\",\n  \"response_format\": \"json\",\n  \"temperature\": 0,\n  \"timestamp_granularities\": [\n    \"segment\"\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://ai.liara.ir/api/{workspaceID}/v1/audio/transcriptions")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"openai/whisper-1\",\n  \"input_audio\": {\n    \"data\": \"UklGRiQAAABXQVZFZm10IBAAAAABAAEA...\",\n    \"format\": \"wav\"\n  },\n  \"language\": \"en\",\n  \"response_format\": \"json\",\n  \"temperature\": 0,\n  \"timestamp_granularities\": [\n    \"segment\"\n  ]\n}"

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

{
  "text": "Hello, this is a transcription test."
}

Authorizations

Authorization

string

header

required

Enter the API key with the Bearer: prefix, e.g. "Bearer "

Path Parameters

workspaceID

string

required

The workspace ID used for billing and routing.

Pattern: ^[a-f0-9]{24}$

Body

model

string

required

The speech-to-text model to use.

The model must be one of the speech-to-text models supported by the API.

Example:

"openai/whisper-1"

input_audio

object

required

Audio data provided as a Base64-encoded string.

This object is used for JSON requests. Multipart requests should provide the audio through the file field instead.

Show child attributes

language

string

The language of the input audio.

Must be a two-letter ISO-639-1 language code.

If omitted, the model may automatically detect the language.

Required string length: 2

Example:

"en"

response_format

enum<string>

default:json

The format of the transcription response.

json returns the standard transcription response.

verbose_json returns additional transcription information, such as language, duration, and timestamp information when supported by the selected model.

Available options:

json,

verbose_json

Example:

"json"

temperature

number<float>

Sampling temperature used during transcription.

Values must be between 0 and 1.

Required range: 0 <= x <= 1

Example:

0

timestamp_granularities

enum<string>[]

Specifies the timestamp granularities to include in the transcription response.

Supported values are word and segment.

Available options:

word,

segment

Example:

["segment"]

Response

Successfully transcribed the audio.

Transcription result returned by the speech-to-text model.

The exact fields may vary depending on the selected response_format and the capabilities of the selected model.

text

string

The transcribed text.

Example:

"Hello, this is a transcription test."

task

string

The transcription task.

Example:

"transcribe"

language

string

Detected or requested language.

Example:

"english"

duration

number<float>

Duration of the input audio in seconds.

Example:

3.52

segments

object[]

Transcription segments with timing information.

Available when supported by the selected model and when requested through timestamp_granularities.

Show child attributes

Introduction

Chat Completions

Image Generation

Embeddings

Text to Speech

Audio Transcriptions

Workspaces

API Keys

Models

Logs

Playground

Transcribe audio

Authorizations

Path Parameters

Body

Response