Create transcription

POST

audio

transcriptions

Python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["COMETAPI_KEY"],
    base_url="https://api.cometapi.com/v1"
)

audio_file = open("audio.mp3", "rb")
transcription = client.audio.transcriptions.create(
    model="whisper-1",
    file=audio_file
)
print(transcription.text)

import OpenAI from "openai";
import fs from "fs";

const client = new OpenAI({
  apiKey: process.env.COMETAPI_KEY,
  baseURL: "https://api.cometapi.com/v1"
});

const transcription = await client.audio.transcriptions.create({
  model: "whisper-1",
  file: fs.createReadStream("audio.mp3")
});
console.log(transcription.text);

curl -X POST https://api.cometapi.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -F model="whisper-1" \
  -F file="@audio.mp3"

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.cometapi.com/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<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nwhisper-1\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: multipart/form-data; boundary=---011000010111000001101001"
  ],
]);

$response = curl_exec($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.cometapi.com/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<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nwhisper-1\r\n-----011000010111000001101001--")

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

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "multipart/form-data; boundary=---011000010111000001101001")

	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.cometapi.com/v1/audio/transcriptions")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "multipart/form-data; boundary=---011000010111000001101001")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nwhisper-1\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.cometapi.com/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["Content-Type"] = 'multipart/form-data; boundary=---011000010111000001101001'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nwhisper-1\r\n-----011000010111000001101001--"

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

{
  "text": "Hello, welcome to CometAPI."
}

Usa questo endpoint per trascrivere l’audio in testo nella lingua di origine. È adatto a note di riunioni, messaggi vocali, indicizzazione dei media, sottotitoli e flussi di supporto che richiedono testo ricercabile.

Prima richiesta

Invia un file audio supportato con model e file. Mantieni il primo file breve mentre verifichi la gestione dell’upload, l’autenticazione e il parsing della risposta.

Leggere la risposta

La risposta predefinita include il text trascritto. Se richiedi un altro formato di risposta, assicurati che il client analizzi quel formato invece di dare per scontata la struttura JSON predefinita.

Passaggi successivi

Usa Create Speech quando hai bisogno di un output text-to-speech.
Usa Create Translation quando l’output di destinazione deve essere in inglese.

Autorizzazioni

Authorization

string

header

obbligatorio

Bearer token authentication. Use your CometAPI key.

Corpo

multipart/form-data

file

obbligatorio

The audio file to transcribe. Supported formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm.

model

string

predefinito:whisper-1

obbligatorio

The speech-to-text model to use. Choose a current speech model from the Models page.

language

string

The language of the input audio in ISO-639-1 format (e.g., en, zh, ja). Supplying the language improves accuracy and latency.

prompt

string

Optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.

response_format

enum<string>

predefinito:json

The output format for the transcription.

Opzioni disponibili:

json,

text,

srt,

verbose_json,

vtt

temperature

number

predefinito:0

Sampling temperature between 0 and 1. Higher values produce more random output; lower values are more focused. When set to 0, the model auto-adjusts temperature using log probability.

Intervallo richiesto: 0 <= x <= 1

Risposta

200 - application/json

The transcription result.

text

string

obbligatorio

The transcribed text.

Create speech

Create translation

Python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["COMETAPI_KEY"],
    base_url="https://api.cometapi.com/v1"
)

audio_file = open("audio.mp3", "rb")
transcription = client.audio.transcriptions.create(
    model="whisper-1",
    file=audio_file
)
print(transcription.text)

import OpenAI from "openai";
import fs from "fs";

const client = new OpenAI({
  apiKey: process.env.COMETAPI_KEY,
  baseURL: "https://api.cometapi.com/v1"
});

const transcription = await client.audio.transcriptions.create({
  model: "whisper-1",
  file: fs.createReadStream("audio.mp3")
});
console.log(transcription.text);

curl -X POST https://api.cometapi.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -F model="whisper-1" \
  -F file="@audio.mp3"

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.cometapi.com/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<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nwhisper-1\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: multipart/form-data; boundary=---011000010111000001101001"
  ],
]);

$response = curl_exec($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.cometapi.com/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<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nwhisper-1\r\n-----011000010111000001101001--")

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

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "multipart/form-data; boundary=---011000010111000001101001")

	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.cometapi.com/v1/audio/transcriptions")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "multipart/form-data; boundary=---011000010111000001101001")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nwhisper-1\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.cometapi.com/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["Content-Type"] = 'multipart/form-data; boundary=---011000010111000001101001'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nwhisper-1\r\n-----011000010111000001101001--"

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

{
  "text": "Hello, welcome to CometAPI."
}

Moderazione dei contenuti

Chiavi API

Prima richiesta

Leggere la risposta

Passaggi successivi

Autorizzazioni

Corpo

Risposta

​Prima richiesta

​Leggere la risposta

​Passaggi successivi

Autorizzazioni

Corpo

Risposta

Prima richiesta

Leggere la risposta

Passaggi successivi