创建转录

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."
}

使用此端点可将音频按源语言转录为文本。它适用于会议记录、语音消息、媒体索引、字幕以及需要可搜索文本的支持工作流。

首次请求

发送一个受支持的音频文件，并提供 model 和 file。在验证上传处理、身份验证和响应解析时，首个文件应尽量保持较短。

读取响应

默认响应包含转录后的 text。如果你请求了其他响应格式，请确保客户端解析该格式，而不是假定为默认的 JSON 结构。

后续步骤

当你需要文本转语音输出时，使用创建语音。
当目标输出应为英语时，使用创建翻译。

授权

Authorization

string

header

必填

Bearer token authentication. Use your CometAPI key.

请求体

multipart/form-data

file

必填

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

model

string

默认值:whisper-1

必填

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>

默认值:json

The output format for the transcription.

可用选项:

json,

text,

srt,

verbose_json,

vtt

temperature

number

默认值: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.

必填范围: 0 <= x <= 1

响应

200 - application/json

The transcription result.

text

string

必填

The transcribed text.

创建语音

创建翻译

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."
}

内容审核

API 密钥

首次请求

读取响应

后续步骤

授权

请求体

响应

​首次请求

​读取响应

​后续步骤

授权

请求体

响应

首次请求

读取响应

后续步骤