Openai Audio Transcriptions

curl --request POST \
  --url https://api.acedata.cloud/v1/audio/transcriptions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form file='@example-file'

import requests

url = "https://api.acedata.cloud/v1/audio/transcriptions"

files = { "file": ("example-file", open("example-file", "rb")) }
headers = {"Authorization": "Bearer <token>"}

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

print(response.text)

const form = new FormData();
form.append('file', '<string>');

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

options.body = form;

fetch('https://api.acedata.cloud/v1/audio/transcriptions', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "text": "Ace Data Cloud Platform is testing the speech recognition endpoint. The quick brown fox jumps over the lazy dog."
}

{
  "error": {
    "code": "bad_request",
    "message": "Please provide an audio `file` to transcribe."
  },
  "trace_id": "2efa9340-b21b-4e26-9e14-4aac95f343ab"
}

{
  "error": {
    "code": "authentication_failed",
    "message": "The token is invalid."
  },
  "trace_id": "2efa9340-b21b-4e26-9e14-4aac95f343ab"
}

{
  "error": {
    "code": "used_up",
    "message": "Your balance is not enough."
  },
  "trace_id": "2efa9340-b21b-4e26-9e14-4aac95f343ab"
}

{
  "error": {
    "code": "request_too_large",
    "message": "File too large"
  },
  "trace_id": "2efa9340-b21b-4e26-9e14-4aac95f343ab"
}

{
  "error": {
    "code": "too_many_requests",
    "message": "Transcription service is busy, please try again later."
  },
  "trace_id": "2efa9340-b21b-4e26-9e14-4aac95f343ab"
}

{
  "error": {
    "code": "api_error",
    "message": "Failed to transcribe the audio, please try again later."
  },
  "trace_id": "2efa9340-b21b-4e26-9e14-4aac95f343ab"
}

POST

audio

transcriptions

Openai Audio Transcriptions

curl --request POST \
  --url https://api.acedata.cloud/v1/audio/transcriptions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form file='@example-file'

import requests

url = "https://api.acedata.cloud/v1/audio/transcriptions"

files = { "file": ("example-file", open("example-file", "rb")) }
headers = {"Authorization": "Bearer <token>"}

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

print(response.text)

const form = new FormData();
form.append('file', '<string>');

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

options.body = form;

fetch('https://api.acedata.cloud/v1/audio/transcriptions', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "text": "Ace Data Cloud Platform is testing the speech recognition endpoint. The quick brown fox jumps over the lazy dog."
}

{
  "error": {
    "code": "bad_request",
    "message": "Please provide an audio `file` to transcribe."
  },
  "trace_id": "2efa9340-b21b-4e26-9e14-4aac95f343ab"
}

{
  "error": {
    "code": "authentication_failed",
    "message": "The token is invalid."
  },
  "trace_id": "2efa9340-b21b-4e26-9e14-4aac95f343ab"
}

{
  "error": {
    "code": "used_up",
    "message": "Your balance is not enough."
  },
  "trace_id": "2efa9340-b21b-4e26-9e14-4aac95f343ab"
}

{
  "error": {
    "code": "request_too_large",
    "message": "File too large"
  },
  "trace_id": "2efa9340-b21b-4e26-9e14-4aac95f343ab"
}

{
  "error": {
    "code": "too_many_requests",
    "message": "Transcription service is busy, please try again later."
  },
  "trace_id": "2efa9340-b21b-4e26-9e14-4aac95f343ab"
}

{
  "error": {
    "code": "api_error",
    "message": "Failed to transcribe the audio, please try again later."
  },
  "trace_id": "2efa9340-b21b-4e26-9e14-4aac95f343ab"
}

Autorizaciones

Authorization

string

header

requerido

API token from https://platform.acedata.cloud

Cuerpo

multipart/form-data

file

requerido

Openai Audio Transcriptions File

model

enum<string>

predeterminado:whisper-1

Openai Audio Transcriptions Model

Opciones disponibles:

whisper-1,

gpt-transcribe

language

string

Openai Audio Transcriptions Language

prompt

string

Openai Audio Transcriptions Prompt

response_format

enum<string>

predeterminado:json

Openai Audio Transcriptions Response Format

Opciones disponibles:

json,

text,

srt,

verbose_json,

vtt

temperature

number

predeterminado:0

Openai Audio Transcriptions Temperature

timestamp_granularities[]

enum<string>[]

Openai Audio Transcriptions Timestamp Granularities

Opciones disponibles:

word,

segment

stream

boolean

predeterminado:false

Openai Audio Transcriptions Stream

languages[]

string[]

Openai Audio Transcriptions Languages

keywords[]

string[]

Openai Audio Transcriptions Keywords

Respuesta

Openai Audio Transcriptions Response 200

text

string

Openai Audio Transcriptions Response 200 Text

Gemini IA

GLM

Kimi

Claude IA

DeepSeek IA

Grok

Generación OpenAI

Diálogo de IA

Generación de imagen ByteDance Seedream

Generación de imagen Nano Banana

Generación de imágenes Flux

Generación Midjourney

Producción de foto de ID de IA

Transformación facial

Generación de código QR artístico

Generación de video ByteDance Seedance

Generación de video Sora

Generación de video Veo

Generación de video Kling

Generación de video Tongyi Wansiang

Generación de video Luma

Generación de video Hailuo

Generación de música Suno

Generación de música Fish

Generación de música Producer

Motor de búsqueda

Generación de enlaces cortos

Información de TikTok

Información de Twitter

traducción de localización

Reconocimiento de códigos de verificación numéricos en inglés

Servicio de reconocimiento de código de verificación Recaptcha

Servicio de reconocimiento de código de verificación hCaptcha

Autenticación de identidad

Proxy de conexión directa ADSL

Openai Audio Transcriptions

Autorizaciones

Cuerpo

Respuesta