Whisper V3 API

Transcribe or translate audio using Whisper Large V3

curl --request POST \
  --url https://http.whisper.proxy.prod.s9t.link/model/infer/whisper \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "audio_data": "base64_encoded_audio_content",
  "language": "en",
  "task": "transcribe",
  "word_timestamps": true,
  "diarization": false,
  "streaming": false,
  "batch_size": 24,
  "length_penalty": 1,
  "patience": 1,
  "vad_onset": 0.5,
  "vad_offset": 0.363
}
'

import requests

url = "https://http.whisper.proxy.prod.s9t.link/model/infer/whisper"

payload = {
    "audio_data": "base64_encoded_audio_content",
    "language": "en",
    "task": "transcribe",
    "word_timestamps": True,
    "diarization": False,
    "streaming": False,
    "batch_size": 24,
    "length_penalty": 1,
    "patience": 1,
    "vad_onset": 0.5,
    "vad_offset": 0.363
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    audio_data: 'base64_encoded_audio_content',
    language: 'en',
    task: 'transcribe',
    word_timestamps: true,
    diarization: false,
    streaming: false,
    batch_size: 24,
    length_penalty: 1,
    patience: 1,
    vad_onset: 0.5,
    vad_offset: 0.363
  })
};

fetch('https://http.whisper.proxy.prod.s9t.link/model/infer/whisper', 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://http.whisper.proxy.prod.s9t.link/model/infer/whisper",
  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([
    'audio_data' => 'base64_encoded_audio_content',
    'language' => 'en',
    'task' => 'transcribe',
    'word_timestamps' => true,
    'diarization' => false,
    'streaming' => false,
    'batch_size' => 24,
    'length_penalty' => 1,
    'patience' => 1,
    'vad_onset' => 0.5,
    'vad_offset' => 0.363
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "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://http.whisper.proxy.prod.s9t.link/model/infer/whisper"

	payload := strings.NewReader("{\n  \"audio_data\": \"base64_encoded_audio_content\",\n  \"language\": \"en\",\n  \"task\": \"transcribe\",\n  \"word_timestamps\": true,\n  \"diarization\": false,\n  \"streaming\": false,\n  \"batch_size\": 24,\n  \"length_penalty\": 1,\n  \"patience\": 1,\n  \"vad_onset\": 0.5,\n  \"vad_offset\": 0.363\n}")

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

	req.Header.Add("Authorization", "Bearer <token>")
	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://http.whisper.proxy.prod.s9t.link/model/infer/whisper")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"audio_data\": \"base64_encoded_audio_content\",\n  \"language\": \"en\",\n  \"task\": \"transcribe\",\n  \"word_timestamps\": true,\n  \"diarization\": false,\n  \"streaming\": false,\n  \"batch_size\": 24,\n  \"length_penalty\": 1,\n  \"patience\": 1,\n  \"vad_onset\": 0.5,\n  \"vad_offset\": 0.363\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://http.whisper.proxy.prod.s9t.link/model/infer/whisper")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"audio_data\": \"base64_encoded_audio_content\",\n  \"language\": \"en\",\n  \"task\": \"transcribe\",\n  \"word_timestamps\": true,\n  \"diarization\": false,\n  \"streaming\": false,\n  \"batch_size\": 24,\n  \"length_penalty\": 1,\n  \"patience\": 1,\n  \"vad_onset\": 0.5,\n  \"vad_offset\": 0.363\n}"

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

{
  "transcription": [
    "Hello, this is a test.",
    "The audio quality is good."
  ],
  "request_time": 2.5,
  "language": "en",
  "segments": [
    {
      "start": 0,
      "end": 2.5,
      "text": "Hello, this is a test.",
      "words": [
        {
          "word": "Hello",
          "start": 0,
          "end": 0.5
        }
      ]
    }
  ]
}

POST

model

infer

whisper

Transcribe or translate audio using Whisper Large V3

curl --request POST \
  --url https://http.whisper.proxy.prod.s9t.link/model/infer/whisper \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "audio_data": "base64_encoded_audio_content",
  "language": "en",
  "task": "transcribe",
  "word_timestamps": true,
  "diarization": false,
  "streaming": false,
  "batch_size": 24,
  "length_penalty": 1,
  "patience": 1,
  "vad_onset": 0.5,
  "vad_offset": 0.363
}
'

import requests

url = "https://http.whisper.proxy.prod.s9t.link/model/infer/whisper"

payload = {
    "audio_data": "base64_encoded_audio_content",
    "language": "en",
    "task": "transcribe",
    "word_timestamps": True,
    "diarization": False,
    "streaming": False,
    "batch_size": 24,
    "length_penalty": 1,
    "patience": 1,
    "vad_onset": 0.5,
    "vad_offset": 0.363
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    audio_data: 'base64_encoded_audio_content',
    language: 'en',
    task: 'transcribe',
    word_timestamps: true,
    diarization: false,
    streaming: false,
    batch_size: 24,
    length_penalty: 1,
    patience: 1,
    vad_onset: 0.5,
    vad_offset: 0.363
  })
};

fetch('https://http.whisper.proxy.prod.s9t.link/model/infer/whisper', 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://http.whisper.proxy.prod.s9t.link/model/infer/whisper",
  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([
    'audio_data' => 'base64_encoded_audio_content',
    'language' => 'en',
    'task' => 'transcribe',
    'word_timestamps' => true,
    'diarization' => false,
    'streaming' => false,
    'batch_size' => 24,
    'length_penalty' => 1,
    'patience' => 1,
    'vad_onset' => 0.5,
    'vad_offset' => 0.363
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "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://http.whisper.proxy.prod.s9t.link/model/infer/whisper"

	payload := strings.NewReader("{\n  \"audio_data\": \"base64_encoded_audio_content\",\n  \"language\": \"en\",\n  \"task\": \"transcribe\",\n  \"word_timestamps\": true,\n  \"diarization\": false,\n  \"streaming\": false,\n  \"batch_size\": 24,\n  \"length_penalty\": 1,\n  \"patience\": 1,\n  \"vad_onset\": 0.5,\n  \"vad_offset\": 0.363\n}")

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

	req.Header.Add("Authorization", "Bearer <token>")
	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://http.whisper.proxy.prod.s9t.link/model/infer/whisper")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"audio_data\": \"base64_encoded_audio_content\",\n  \"language\": \"en\",\n  \"task\": \"transcribe\",\n  \"word_timestamps\": true,\n  \"diarization\": false,\n  \"streaming\": false,\n  \"batch_size\": 24,\n  \"length_penalty\": 1,\n  \"patience\": 1,\n  \"vad_onset\": 0.5,\n  \"vad_offset\": 0.363\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://http.whisper.proxy.prod.s9t.link/model/infer/whisper")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"audio_data\": \"base64_encoded_audio_content\",\n  \"language\": \"en\",\n  \"task\": \"transcribe\",\n  \"word_timestamps\": true,\n  \"diarization\": false,\n  \"streaming\": false,\n  \"batch_size\": 24,\n  \"length_penalty\": 1,\n  \"patience\": 1,\n  \"vad_onset\": 0.5,\n  \"vad_offset\": 0.363\n}"

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

{
  "transcription": [
    "Hello, this is a test.",
    "The audio quality is good."
  ],
  "request_time": 2.5,
  "language": "en",
  "segments": [
    {
      "start": 0,
      "end": 2.5,
      "text": "Hello, this is a test.",
      "words": [
        {
          "word": "Hello",
          "start": 0,
          "end": 0.5
        }
      ]
    }
  ]
}

Authorizations

Authorization

string

header

required

JWT token for authentication

Body

application/json

audio_data

string

required

TEXT FIELD: This is a string field (not a file upload). Provide the audio as a base64-encoded string. First convert your audio file (.mp3, .wav, .flac) to base64, then paste the resulting string here.

Example:

"base64_encoded_audio_content"

language

string

required

Language code (e.g. 'en' for English)

Example:

"en"

task

enum<string>

required

Task type - transcribe in source language or translate to English

Available options:

transcribe,

translate

Example:

"transcribe"

initial_prompt

string

Optional starting text prompt for context

Example:

"Meeting transcript between John and Sarah:"

beam_size

integer

default:5

Number of parallel sequences evaluated

Required range: 1 <= x <= 5

best_of

integer

default:5

Number of best sequences considered

Required range: 1 <= x <= 5

word_timestamps

boolean

default:false

Include word-level timestamps

diarization

boolean

default:false

Enable speaker diarization

vad_filter

boolean

default:true

Enable voice activity detection filter

without_timestamps

boolean

default:false

Exclude timestamps from output

streaming

boolean

default:false

Enable streaming output

min_speakers

integer

default:0

Minimum number of speakers to detect (0 for automatic)

Required range: x >= 0

max_speakers

integer

default:0

Maximum number of speakers to detect (0 for automatic)

Required range: x >= 0

batch_size

integer

default:24

Number of audio samples processed in one batch

Required range: 0 <= x <= 24

length_penalty

number

default:1

Penalty for longer sequences (1.0 means no penalty)

Required range: x >= 0

patience

number

default:1

Beam search patience factor

Required range: 0 <= x <= 1

min_duration_off

number

default:0

Minimum duration of silence for a break (seconds)

Required range: x >= 0

min_duration_on

number

default:0

Minimum duration for speech detection (seconds)

Required range: x >= 0

vad_onset

number

default:0.5

Voice activity detection onset threshold

Required range: 0 <= x <= 1

vad_offset

number

default:0.363

Voice activity detection offset threshold

Required range: 0 <= x <= 1

pad_offset

number

default:0

Additional padding at segment end (seconds)

Required range: x >= 0

pad_onset

number

default:0

Additional padding at segment start (seconds)

Required range: x >= 0

max_duration

number

default:30

Maximum duration to process (seconds)

Required range: x >= 0

Response

Successful transcription

transcription

string[]

required

Array of transcribed text segments

Example:

[
  "Hello, this is a test.",
  "The audio quality is good."
]

request_time

number

required

Total processing time in seconds

Example:

2.5

language

string

required

Detected or specified language

Example:

"en"

segments

object[]

Show child attributes

⌘I

API Documentation

Inference APIs

Training APIs

Authorizations

Body

Response