전사 API (Beta)

Transcribes audio into the input language.

Authentication: This endpoint accepts either a Bearer API key or a SIGN-IN-WITH-X header for x402 wallet-based authentication. The legacy X-Sign-In-With-X header is also accepted during migration. When using x402, a 402 Payment Required response indicates insufficient balance and includes top-up instructions.

POST /audio/transcriptions

/api/v1/audio/transcriptions

cURL

curl --request POST \
  --url https://api.venice.ai/api/v1/audio/transcriptions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form file='@example-file' \
  --form model=openai/whisper-large-v3 \
  --form response_format=json \
  --form timestamps=false

import requests

url = "https://api.venice.ai/api/v1/audio/transcriptions"

files = { "file": ("example-file", open("example-file", "rb")) }
payload = {
    "model": "openai/whisper-large-v3",
    "response_format": "json",
    "timestamps": "false"
}
headers = {"Authorization": "Bearer <token>"}

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

print(response.text)

const form = new FormData();
form.append('file', '[audio file]');
form.append('model', 'openai/whisper-large-v3');
form.append('response_format', 'json');
form.append('timestamps', 'false');

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

options.body = form;

fetch('https://api.venice.ai/api/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://api.venice.ai/api/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 => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n[audio file]\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nopenai/whisper-large-v3\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"timestamps\"\r\n\r\nfalse\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "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.venice.ai/api/v1/audio/transcriptions"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n[audio file]\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nopenai/whisper-large-v3\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"timestamps\"\r\n\r\nfalse\r\n-----011000010111000001101001--")

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

	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.venice.ai/api/v1/audio/transcriptions")
  .header("Authorization", "Bearer <token>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n[audio file]\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nopenai/whisper-large-v3\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"timestamps\"\r\n\r\nfalse\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.venice.ai/api/v1/audio/transcriptions")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n[audio file]\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nopenai/whisper-large-v3\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"timestamps\"\r\n\r\nfalse\r\n-----011000010111000001101001--"

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

200

{
  "text": "<string>",
  "duration": 123,
  "timestamps": {
    "word": [
      {
        "word": "<string>",
        "start": 123,
        "end": 123
      }
    ],
    "segment": [
      {
        "text": "<string>",
        "start": 123,
        "end": 123
      }
    ],
    "char": [
      {
        "char": "<string>",
        "start": 123,
        "end": 123
      }
    ]
  }
}

{
  "error": "<string>",
  "details": {
    "_errors": [],
    "field": {
      "_errors": [
        "Field is required"
      ]
    }
  }
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "code": "PAYLOAD_TOO_LARGE",
  "error": "File exceeds the maximum allowed size of 25 MB."
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

인증

BearerAuthsiwx

Authorization · string · header · 필수

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

본문

multipart/form-data

Request to transcribe audio to text.

file · file

The audio file object (not a base64 string). Supported formats: WAV, WAVE, FLAC, M4A, AAC, MP4, MP3, OGG, OGA, WEBM.

model · enum<string> · 기본값: nvidia/parakeet-tdt-0.6b-v3

The model to use for transcription. See https://docs.venice.ai/models/overview for more information.

사용 가능한 옵션: nvidia/parakeet-tdt-0.6b-v3, openai/whisper-large-v3, fal-ai/wizper, elevenlabs/scribe-v2, stt-xai-v1

예시:

"openai/whisper-large-v3"

response_format · enum<string> · 기본값: json

The format of the transcript output, in one of these options: json, text.

사용 가능한 옵션: json, text

예시:

"json"

timestamps · boolean · 기본값: false

Whether to include timestamps in the response.

예시:

false

language · string

ISO 639-1 language code (e.g., "en", "es", "fr"). Optional - if not provided, the model will auto-detect the language. Note: Only supported by certain models (e.g., Whisper). Ignored by models that do not support language hints.

예시:

"en"

응답

200

application/json

Transcription completed successfully

Transcription response

text · string · 필수

The transcribed text

duration · number

Duration of the audio in seconds

timestamps · object

Timestamps for the transcription (only if timestamps=true)

Show child attributes