语音转写

语音转写

curl --request POST \
  --url https://api.tikway.ai/v1/audio/transcriptions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form file=@example-file \
  --form model=@example-file \
  --form language=zh \
  --form 'languages=zh,en' \
  --form 'prompt=会议纪要术语：Tikway' \
  --form 'keywords=Tikway,API' \
  --form response_format=json \
  --form temperature=0 \
  --form stream=false \
  --form chunking_strategy=auto \
  --form 'known_speaker_names=Alice,Bob' \
  --form 'known_speaker_references="data:audio/wav;base64,UklGRg=="'

import requests

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

files = {
    "file": ("example-file", open("example-file", "rb")),
    "model": ("example-file", open("example-file", "rb"))
}
payload = {
    "language": "zh",
    "languages": "zh,en",
    "prompt": "会议纪要术语：Tikway",
    "keywords": "Tikway,API",
    "response_format": "json",
    "temperature": "0",
    "stream": "false",
    "chunking_strategy": "auto",
    "known_speaker_names": "Alice,Bob",
    "known_speaker_references": "data:audio/wav;base64,UklGRg=="
}
headers = {"Authorization": "Bearer <token>"}

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

print(response.text)

const form = new FormData();
form.append('file', 'example-file');
form.append('model', 'gpt-4o-transcribe');
form.append('language', 'zh');
form.append('languages', 'zh,en');
form.append('prompt', '会议纪要术语：Tikway');
form.append('keywords', 'Tikway,API');
form.append('response_format', 'json');
form.append('temperature', '0');
form.append('stream', 'false');
form.append('chunking_strategy', 'auto');
form.append('known_speaker_names', 'Alice,Bob');
form.append('known_speaker_references', 'data:audio/wav;base64,UklGRg==');

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

options.body = form;

fetch('https://api.tikway.ai/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.tikway.ai/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\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\ngpt-4o-transcribe\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\nzh\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"languages\"\r\n\r\nzh,en\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"prompt\"\r\n\r\n会议纪要术语：Tikway\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"keywords\"\r\n\r\nTikway,API\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n0\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"stream\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunking_strategy\"\r\n\r\nauto\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"known_speaker_names\"\r\n\r\nAlice,Bob\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"known_speaker_references\"\r\n\r\ndata:audio/wav;base64,UklGRg==\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.tikway.ai/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\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\ngpt-4o-transcribe\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\nzh\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"languages\"\r\n\r\nzh,en\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"prompt\"\r\n\r\n会议纪要术语：Tikway\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"keywords\"\r\n\r\nTikway,API\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n0\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"stream\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunking_strategy\"\r\n\r\nauto\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"known_speaker_names\"\r\n\r\nAlice,Bob\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"known_speaker_references\"\r\n\r\ndata:audio/wav;base64,UklGRg==\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.tikway.ai/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\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\ngpt-4o-transcribe\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\nzh\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"languages\"\r\n\r\nzh,en\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"prompt\"\r\n\r\n会议纪要术语：Tikway\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"keywords\"\r\n\r\nTikway,API\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n0\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"stream\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunking_strategy\"\r\n\r\nauto\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"known_speaker_names\"\r\n\r\nAlice,Bob\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"known_speaker_references\"\r\n\r\ndata:audio/wav;base64,UklGRg==\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.tikway.ai/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\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\ngpt-4o-transcribe\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\nzh\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"languages\"\r\n\r\nzh,en\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"prompt\"\r\n\r\n会议纪要术语：Tikway\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"keywords\"\r\n\r\nTikway,API\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n0\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"stream\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunking_strategy\"\r\n\r\nauto\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"known_speaker_names\"\r\n\r\nAlice,Bob\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"known_speaker_references\"\r\n\r\ndata:audio/wav;base64,UklGRg==\r\n-----011000010111000001101001--"

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

{
  "text": "今天会议主要讨论了新版本的发布时间。",
  "usage": {
    "type": "tokens",
    "input_tokens": 120,
    "input_token_details": {
      "text_tokens": 0,
      "audio_tokens": 120
    },
    "output_tokens": 18,
    "total_tokens": 138
  }
}

POST

https://api.tikway.ai

audio

transcriptions

语音转写

curl --request POST \
  --url https://api.tikway.ai/v1/audio/transcriptions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form file=@example-file \
  --form model=@example-file \
  --form language=zh \
  --form 'languages=zh,en' \
  --form 'prompt=会议纪要术语：Tikway' \
  --form 'keywords=Tikway,API' \
  --form response_format=json \
  --form temperature=0 \
  --form stream=false \
  --form chunking_strategy=auto \
  --form 'known_speaker_names=Alice,Bob' \
  --form 'known_speaker_references="data:audio/wav;base64,UklGRg=="'

import requests

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

files = {
    "file": ("example-file", open("example-file", "rb")),
    "model": ("example-file", open("example-file", "rb"))
}
payload = {
    "language": "zh",
    "languages": "zh,en",
    "prompt": "会议纪要术语：Tikway",
    "keywords": "Tikway,API",
    "response_format": "json",
    "temperature": "0",
    "stream": "false",
    "chunking_strategy": "auto",
    "known_speaker_names": "Alice,Bob",
    "known_speaker_references": "data:audio/wav;base64,UklGRg=="
}
headers = {"Authorization": "Bearer <token>"}

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

print(response.text)

const form = new FormData();
form.append('file', 'example-file');
form.append('model', 'gpt-4o-transcribe');
form.append('language', 'zh');
form.append('languages', 'zh,en');
form.append('prompt', '会议纪要术语：Tikway');
form.append('keywords', 'Tikway,API');
form.append('response_format', 'json');
form.append('temperature', '0');
form.append('stream', 'false');
form.append('chunking_strategy', 'auto');
form.append('known_speaker_names', 'Alice,Bob');
form.append('known_speaker_references', 'data:audio/wav;base64,UklGRg==');

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

options.body = form;

fetch('https://api.tikway.ai/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.tikway.ai/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\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\ngpt-4o-transcribe\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\nzh\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"languages\"\r\n\r\nzh,en\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"prompt\"\r\n\r\n会议纪要术语：Tikway\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"keywords\"\r\n\r\nTikway,API\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n0\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"stream\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunking_strategy\"\r\n\r\nauto\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"known_speaker_names\"\r\n\r\nAlice,Bob\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"known_speaker_references\"\r\n\r\ndata:audio/wav;base64,UklGRg==\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.tikway.ai/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\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\ngpt-4o-transcribe\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\nzh\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"languages\"\r\n\r\nzh,en\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"prompt\"\r\n\r\n会议纪要术语：Tikway\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"keywords\"\r\n\r\nTikway,API\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n0\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"stream\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunking_strategy\"\r\n\r\nauto\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"known_speaker_names\"\r\n\r\nAlice,Bob\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"known_speaker_references\"\r\n\r\ndata:audio/wav;base64,UklGRg==\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.tikway.ai/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\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\ngpt-4o-transcribe\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\nzh\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"languages\"\r\n\r\nzh,en\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"prompt\"\r\n\r\n会议纪要术语：Tikway\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"keywords\"\r\n\r\nTikway,API\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n0\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"stream\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunking_strategy\"\r\n\r\nauto\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"known_speaker_names\"\r\n\r\nAlice,Bob\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"known_speaker_references\"\r\n\r\ndata:audio/wav;base64,UklGRg==\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.tikway.ai/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\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\ngpt-4o-transcribe\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\nzh\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"languages\"\r\n\r\nzh,en\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"prompt\"\r\n\r\n会议纪要术语：Tikway\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"keywords\"\r\n\r\nTikway,API\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n0\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"stream\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunking_strategy\"\r\n\r\nauto\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"known_speaker_names\"\r\n\r\nAlice,Bob\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"known_speaker_references\"\r\n\r\ndata:audio/wav;base64,UklGRg==\r\n-----011000010111000001101001--"

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

{
  "text": "今天会议主要讨论了新版本的发布时间。",
  "usage": {
    "type": "tokens",
    "input_tokens": 120,
    "input_token_details": {
      "text_tokens": 0,
      "audio_tokens": 120
    },
    "output_tokens": 18,
    "total_tokens": 138
  }
}

授权

Authorization

string

header

必填

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

请求体

multipart/form-data

file

必填

待转写的音频文件。

model

file

必填

语音转写模型 ID。

language

string

输入音频语言，建议使用 ISO 639-1 语言代码。

示例:

"zh"

languages

string[]

可能出现的语言代码。

示例:

"zh,en"

prompt

string

用于指导转写风格、术语和上下文的提示词。

示例:

"会议纪要术语：Tikway"

keywords

string[]

需要重点识别的词语或短语。

示例:

"Tikway,API"

response_format

string

响应格式。

示例:

"json"

temperature

string

采样温度。

示例:

"0"

stream

number

是否使用 SSE 流式返回。

示例:

"false"

chunking_strategy

boolean

分块策略。

示例:

"auto"

known_speaker_names

string[]

已知说话人名称。

示例:

"Alice,Bob"

known_speaker_references

string[]

已知说话人的音频 Base64 data URL。

示例:

"data:audio/wav;base64,UklGRg=="

响应

200 - application/json

非流式语音转写 JSON 响应。兼容普通转写、详细时间戳转写和说话人分离结果。

text

string

必填

完整转写文本。

task

string

任务类型。详细 JSON 和说话人分离响应通常返回该字段。

Allowed value: "transcribe"

language

string

检测或使用的音频语言。

duration

number

音频时长，单位为秒。

必填范围: x >= 0

words

object[]

词级时间戳，仅请求 word 粒度时返回。

Hide child attributes

words.word

string

必填

words.start

number

必填

必填范围: x >= 0

words.end

number

必填

必填范围: x >= 0

segments

object[]

分段转写结果。verbose_json 返回时间戳分段；diarized_json 还会返回说话人信息。

Hide child attributes

segments.start

number

必填

必填范围: x >= 0

segments.end

number

必填

必填范围: x >= 0

segments.text

string

必填

segments.type

string

说话人分离分段通常固定为 transcript.text.segment。

segments.id

segments.seek

integer

必填范围: x >= 0

segments.speaker

string

说话人名称或系统生成的说话人标签。

segments.tokens

integer[]

必填范围: x >= 0

segments.temperature

number

segments.avg_logprob

number

segments.compression_ratio

number

segments.no_speech_prob

number

logprobs

object[]

请求 include[]=logprobs 时可能返回。

Hide child attributes

logprobs.token

string

必填

logprobs.logprob

number

必填

logprobs.bytes

integer[]

必填

必填范围: 0 <= x <= 255

usage

TokenUsage · object

上游返回的 token 或音频时长用量。

TokenUsage
DurationUsage

Hide child attributes

usage.type

string

必填

Allowed value: "tokens"

usage.input_tokens

integer

必填

必填范围: x >= 0

usage.output_tokens

integer

必填

必填范围: x >= 0

usage.total_tokens

integer

必填

必填范围: x >= 0

usage.input_token_details

object

Hide child attributes

usage.input_token_details.text_tokens

integer

必填范围: x >= 0

usage.input_token_details.audio_tokens

integer

必填范围: x >= 0

对话补全

图片生成

Midjourney

视频生成

向量嵌入

语音合成

决策评估

实用接口

语音转写

授权

请求体

响应