SilkDock
API

Speech-to-Text

Transcribe audio to text.

Parameters

ParameterTypeRequiredDescription
modelstringYesTranscription model ID, e.g. whisper-1.
filefileYesAudio file (mp3/mp4/mpeg/mpga/m4a/wav/webm, max 25MB).
languagestringNoISO-639-1 language code, e.g. en, zh. Auto-detected if omitted.
promptstringNoOptional text to guide the model's style or continue a previous segment.
response_formatstringNojson (default), text, srt, verbose_json, vtt.
temperaturenumberNoSampling temperature 0–1. Default: 0.

Endpoint: POST /v1/audio/transcriptions (multipart/form-data)

Examples

curl -X POST https://silkdock.ai/v1/audio/transcriptions \-H "Authorization: Bearer $SILKDOCK_API_KEY" \-F "model=whisper-1" \-F "[email protected]" \-F "language=en"
curl -X POST https://silkdock.ai/v1/audio/transcriptions ^-H "Authorization: Bearer %SILKDOCK_API_KEY%" ^-F "model=whisper-1" ^-F "[email protected]" ^-F "language=en"
http -f POST https://silkdock.ai/v1/audio/transcriptions \Authorization:"Bearer $SILKDOCK_API_KEY" \model=whisper-1 \language=en \[email protected]
# wget does not natively support multipart/form-data file uploads.# Use curl instead:curl -X POST https://silkdock.ai/v1/audio/transcriptions \-H "Authorization: Bearer $SILKDOCK_API_KEY" \-F "model=whisper-1" \-F "[email protected]" \-F "language=en"
$response = Invoke-RestMethod -Uri "https://silkdock.ai/v1/audio/transcriptions" `-Method Post `-Headers @{ Authorization = "Bearer $env:SILKDOCK_API_KEY" } `-Form @{  model    = "whisper-1"  language = "en"  file     = Get-Item -Path "audio.mp3"}Write-Output $response.text
const { OpenAI } = require("openai");const fs = require("fs");const client = new OpenAI({apiKey: process.env.SILKDOCK_API_KEY,baseURL: "https://silkdock.ai/v1",});const transcript = await client.audio.transcriptions.create({model: "whisper-1",file: fs.createReadStream("audio.mp3"),language: "en",});console.log(transcript.text);
import { readFileSync } from "fs";const form = new FormData();form.append("model", "whisper-1");form.append("file", new Blob([readFileSync("audio.mp3")], { type: "audio/mpeg" }), "audio.mp3");form.append("language", "en");const res = await fetch("https://silkdock.ai/v1/audio/transcriptions", {method: "POST",headers: { "Authorization": `Bearer ${process.env.SILKDOCK_API_KEY}` },body: form,});const { text } = await res.json();console.log(text);
import axios from "axios";import { readFileSync } from "fs";import FormData from "form-data";const form = new FormData();form.append("model", "whisper-1");form.append("language", "en");form.append("file", readFileSync("audio.mp3"), {filename: "audio.mp3",contentType: "audio/mpeg",});const { data } = await axios.post("https://silkdock.ai/v1/audio/transcriptions",form,{  headers: {    Authorization: `Bearer ${process.env.SILKDOCK_API_KEY}`,    ...form.getHeaders(),  },});console.log(data.text);
const form = new FormData();form.append("model", "whisper-1");form.append("language", "en");form.append("file", fileInput.files[0]); // fileInput is an <input type="file"> element$.ajax({url: "https://silkdock.ai/v1/audio/transcriptions",type: "POST",headers: { Authorization: `Bearer ${SILKDOCK_API_KEY}` },data: form,processData: false,contentType: false,success(data) {  console.log(data.text);},});
const form = new FormData();form.append("model", "whisper-1");form.append("language", "en");form.append("file", fileInput.files[0]); // fileInput is an <input type="file"> elementconst xhr = new XMLHttpRequest();xhr.open("POST", "https://silkdock.ai/v1/audio/transcriptions");xhr.setRequestHeader("Authorization", `Bearer ${SILKDOCK_API_KEY}`);xhr.onload = () => {const data = JSON.parse(xhr.responseText);console.log(data.text);};xhr.send(form);
const request = require("request");const fs = require("fs");request.post({  url: "https://silkdock.ai/v1/audio/transcriptions",  headers: { Authorization: `Bearer ${process.env.SILKDOCK_API_KEY}` },  formData: {    model: "whisper-1",    language: "en",    file: {      value: fs.createReadStream("audio.mp3"),      options: { filename: "audio.mp3", contentType: "audio/mpeg" },    },  },},(err, _res, body) => {  if (err) throw err;  console.log(JSON.parse(body).text);});
const unirest = require("unirest");const fs = require("fs");unirest.post("https://silkdock.ai/v1/audio/transcriptions").headers({ Authorization: `Bearer ${process.env.SILKDOCK_API_KEY}` }).field("model", "whisper-1").field("language", "en").attach("file", fs.createReadStream("audio.mp3")).then((res) => console.log(res.body.text));
import OpenAI from "openai";import fs from "fs";const client = new OpenAI({apiKey: process.env.SILKDOCK_API_KEY,baseURL: "https://silkdock.ai/v1",});const transcript = await client.audio.transcriptions.create({model: "whisper-1",file: fs.createReadStream("audio.mp3"),language: "en",});console.log(transcript.text);
import { readFileSync } from "fs";const form = new FormData();form.append("model", "whisper-1");form.append("file", new Blob([readFileSync("audio.mp3")], { type: "audio/mpeg" }), "audio.mp3");form.append("language", "en");const res = await fetch("https://silkdock.ai/v1/audio/transcriptions", {method: "POST",headers: {  "Authorization": `Bearer ${process.env.SILKDOCK_API_KEY}`,},body: form,});console.log((await res.json()).text);
import requests, oswith open("audio.mp3", "rb") as f:  res = requests.post(      "https://silkdock.ai/v1/audio/transcriptions",      headers={"Authorization": f"Bearer {os.getenv('SILKDOCK_API_KEY')}"},      files={"file": ("audio.mp3", f, "audio/mpeg")},      data={"model": "whisper-1", "language": "en"},  )print(res.json()["text"])
import osfrom openai import OpenAIclient = OpenAI(  api_key=os.getenv("SILKDOCK_API_KEY"),  base_url="https://silkdock.ai/v1")with open("audio.mp3", "rb") as f:  transcript = client.audio.transcriptions.create(      model="whisper-1",      file=f,      language="en"  )print(transcript.text)
#include <stdio.h>#include <stdlib.h>#include <curl/curl.h>int main(void) {  CURL *curl = curl_easy_init();  if (!curl) return 1;  const char *api_key = getenv("SILKDOCK_API_KEY");  char auth_header[256];  snprintf(auth_header, sizeof(auth_header), "Authorization: Bearer %s", api_key);  struct curl_slist *headers = NULL;  headers = curl_slist_append(headers, auth_header);  curl_mime *mime = curl_mime_init(curl);  curl_mimepart *part = curl_mime_addpart(mime);  curl_mime_name(part, "model");  curl_mime_data(part, "whisper-1", CURL_ZERO_TERMINATED);  part = curl_mime_addpart(mime);  curl_mime_name(part, "language");  curl_mime_data(part, "en", CURL_ZERO_TERMINATED);  part = curl_mime_addpart(mime);  curl_mime_name(part, "file");  curl_mime_filedata(part, "audio.mp3");  curl_mime_type(part, "audio/mpeg");  curl_easy_setopt(curl, CURLOPT_URL, "https://silkdock.ai/v1/audio/transcriptions");  curl_easy_setopt(curl, CURLOPT_HTTPHEADER, headers);  curl_easy_setopt(curl, CURLOPT_MIMEPOST, mime);  CURLcode res = curl_easy_perform(curl);  if (res != CURLE_OK)      fprintf(stderr, "curl_easy_perform() failed: %s\n", curl_easy_strerror(res));  curl_mime_free(mime);  curl_slist_free_all(headers);  curl_easy_cleanup(curl);  return 0;}
#import <Foundation/Foundation.h>int main(int argc, const char *argv[]) {  @autoreleasepool {      NSString *apiKey = [NSProcessInfo processInfo].environment[@"SILKDOCK_API_KEY"];      NSString *boundary = [[NSUUID UUID] UUIDString];      NSURL *url = [NSURL URLWithString:@"https://silkdock.ai/v1/audio/transcriptions"];      NSMutableURLRequest *request = [NSMutableURLRequest requestWithURL:url];      request.HTTPMethod = @"POST";      [request setValue:[NSString stringWithFormat:@"Bearer %@", apiKey]     forHTTPHeaderField:@"Authorization"];      [request setValue:[NSString stringWithFormat:@"multipart/form-data; boundary=%@", boundary]     forHTTPHeaderField:@"Content-Type"];      NSMutableData *body = [NSMutableData data];      // model field      [body appendData:[[NSString stringWithFormat:          @"--%@
Content-Disposition: form-data; name="model"

whisper-1
", boundary]          dataUsingEncoding:NSUTF8StringEncoding]];      // language field      [body appendData:[[NSString stringWithFormat:          @"--%@
Content-Disposition: form-data; name="language"

en
", boundary]          dataUsingEncoding:NSUTF8StringEncoding]];      // file field      NSData *audioData = [NSData dataWithContentsOfFile:@"audio.mp3"];      [body appendData:[[NSString stringWithFormat:          @"--%@
Content-Disposition: form-data; name="file"; filename="audio.mp3"
Content-Type: audio/mpeg

",          boundary] dataUsingEncoding:NSUTF8StringEncoding]];      [body appendData:audioData];      [body appendData:[@"
" dataUsingEncoding:NSUTF8StringEncoding]];      // closing boundary      [body appendData:[[NSString stringWithFormat:@"--%@--
", boundary]          dataUsingEncoding:NSUTF8StringEncoding]];      request.HTTPBody = body;      dispatch_semaphore_t sema = dispatch_semaphore_create(0);      [[[NSURLSession sharedSession] dataTaskWithRequest:request          completionHandler:^(NSData *data, NSURLResponse *response, NSError *error) {              if (data) {                  NSDictionary *json = [NSJSONSerialization JSONObjectWithData:data options:0 error:nil];                  NSLog(@"%@", json[@"text"]);              }              dispatch_semaphore_signal(sema);          }] resume];      dispatch_semaphore_wait(sema, DISPATCH_TIME_FOREVER);  }  return 0;}
import com.openai.client.OpenAIClient;import com.openai.client.okhttp.OpenAIOkHttpClient;import com.openai.models.*;import java.nio.file.Path;OpenAIClient client = OpenAIOkHttpClient.builder()  .apiKey(System.getenv("SILKDOCK_API_KEY"))  .baseURL("https://silkdock.ai/v1")  .build();Transcription transcription = client.audio().transcriptions().create(  TranscriptionCreateParams.builder()      .model(AudioModel.WHISPER_1)      .file(Path.of("audio.mp3"))      .build());System.out.println(transcription.text());
import java.net.http.*;import java.net.URI;import java.nio.file.*;import java.util.UUID;String boundary = UUID.randomUUID().toString();byte[] fileBytes = Files.readAllBytes(Path.of("audio.mp3"));String partHeader = "--" + boundary + "
"  + "Content-Disposition: form-data; name="file"; filename="audio.mp3"
"  + "Content-Type: audio/mpeg

";String modelPart = "--" + boundary + "
"  + "Content-Disposition: form-data; name="model"

whisper-1
";String closing = "--" + boundary + "--
";var body = java.io.ByteArrayOutputStream();body.write(modelPart.getBytes());body.write(partHeader.getBytes());body.write(fileBytes);body.write(("
" + closing).getBytes());var req = HttpRequest.newBuilder()  .uri(URI.create("https://silkdock.ai/v1/audio/transcriptions"))  .header("Authorization", "Bearer " + System.getenv("SILKDOCK_API_KEY"))  .header("Content-Type", "multipart/form-data; boundary=" + boundary)  .POST(HttpRequest.BodyPublishers.ofByteArray(body.toByteArray()))  .build();System.out.println(HttpClient.newHttpClient().send(req, HttpResponse.BodyHandlers.ofString()).body());
import okhttp3.*;import java.io.File;import java.io.IOException;OkHttpClient client = new OkHttpClient();RequestBody requestBody = new MultipartBody.Builder()  .setType(MultipartBody.FORM)  .addFormDataPart("model", "whisper-1")  .addFormDataPart("language", "en")  .addFormDataPart("file", "audio.mp3",      RequestBody.create(new File("audio.mp3"), MediaType.parse("audio/mpeg")))  .build();Request request = new Request.Builder()  .url("https://silkdock.ai/v1/audio/transcriptions")  .header("Authorization", "Bearer " + System.getenv("SILKDOCK_API_KEY"))  .post(requestBody)  .build();try (Response response = client.newCall(request).execute()) {  System.out.println(response.body().string());}
import kong.unirest.Unirest;import java.io.File;var response = Unirest.post("https://silkdock.ai/v1/audio/transcriptions")  .header("Authorization", "Bearer " + System.getenv("SILKDOCK_API_KEY"))  .field("model", "whisper-1")  .field("language", "en")  .field("file", new File("audio.mp3"), "audio/mpeg")  .asJson();System.out.println(response.getBody().getObject().getString("text"));
package mainimport (  "context"  "fmt"  "os"  "github.com/openai/openai-go"  "github.com/openai/openai-go/option")func main() {  client := openai.NewClient(      option.WithAPIKey(os.Getenv("SILKDOCK_API_KEY")),      option.WithBaseURL("https://silkdock.ai/v1"),  )  f, _ := os.Open("audio.mp3")  defer f.Close()  resp, _ := client.Audio.Transcriptions.New(context.Background(),      openai.AudioTranscriptionNewParams{          Model: openai.F(openai.AudioModelWhisper1),          File:  openai.F(f),      },  )  fmt.Println(resp.Text)}
package mainimport (  "bytes"  "fmt"  "io"  "mime/multipart"  "net/http"  "os"  "path/filepath")func main() {  var buf bytes.Buffer  w := multipart.NewWriter(&buf)  w.WriteField("model", "whisper-1")  w.WriteField("language", "en")  f, _ := os.Open("audio.mp3")  defer f.Close()  part, _ := w.CreateFormFile("file", filepath.Base("audio.mp3"))  io.Copy(part, f)  w.Close()  req, _ := http.NewRequest("POST", "https://silkdock.ai/v1/audio/transcriptions", &buf)  req.Header.Set("Authorization", "Bearer "+os.Getenv("SILKDOCK_API_KEY"))  req.Header.Set("Content-Type", w.FormDataContentType())  resp, _ := http.DefaultClient.Do(req)  defer resp.Body.Close()  data, _ := io.ReadAll(resp.Body)  fmt.Println(string(data))}
<?php$ch = curl_init("https://silkdock.ai/v1/audio/transcriptions");curl_setopt_array($ch, [  CURLOPT_POST           => true,  CURLOPT_RETURNTRANSFER => true,  CURLOPT_HTTPHEADER     => [      "Authorization: Bearer " . getenv("SILKDOCK_API_KEY"),  ],  CURLOPT_POSTFIELDS => [      "model"    => "whisper-1",      "language" => "en",      "file"     => new CURLFile("audio.mp3", "audio/mpeg", "audio.mp3"),  ],]);$res = json_decode(curl_exec($ch), true);echo $res["text"];
<?phprequire_once "HTTP/Request2.php";$request = new HTTP_Request2("https://silkdock.ai/v1/audio/transcriptions",  HTTP_Request2::METHOD_POST);$request->setHeader("Authorization", "Bearer " . getenv("SILKDOCK_API_KEY"));$request->addPostParameter("model", "whisper-1");$request->addPostParameter("language", "en");$request->addUpload("file", "audio.mp3", "audio.mp3", "audio/mpeg");$response = $request->send();$data = json_decode($response->getBody(), true);echo $data["text"];
<?phprequire "vendor/autoload.php";use GuzzleHttpClient;$client = new Client();$response = $client->post("https://silkdock.ai/v1/audio/transcriptions", [  "headers" => [      "Authorization" => "Bearer " . getenv("SILKDOCK_API_KEY"),  ],  "multipart" => [      ["name" => "model",    "contents" => "whisper-1"],      ["name" => "language", "contents" => "en"],      [          "name"     => "file",          "contents" => fopen("audio.mp3", "r"),          "filename" => "audio.mp3",          "headers"  => ["Content-Type" => "audio/mpeg"],      ],  ],]);$data = json_decode($response->getBody(), true);echo $data["text"];
<?php$client = new httpClient();$request = new httpClientRequest("POST",  "https://silkdock.ai/v1/audio/transcriptions");$request->setHeaders([  "Authorization" => "Bearer " . getenv("SILKDOCK_API_KEY"),]);$body = new httpMessageBody();$body->addForm(  ["model" => "whisper-1", "language" => "en"],  [      [          "name"    => "file",          "type"    => "audio/mpeg",          "file"    => "audio.mp3",          "data"    => null,      ],  ]);$request->setBody($body);$client->enqueue($request)->send();$response = $client->getResponse();$data = json_decode($response->getBody(), true);echo $data["text"];
import OpenAIlet client = OpenAI(configuration: .init(  token: ProcessInfo.processInfo.environment["SILKDOCK_API_KEY"]!,  host: "silkdock.ai",  scheme: "https"))let query = AudioTranscriptionQuery(  file: try! Data(contentsOf: URL(fileURLWithPath: "audio.mp3")),  fileType: .mp3,  model: "whisper-1")let result = try await client.audioTranscriptions(query: query)print(result.text)
import Foundationlet boundary = UUID().uuidStringvar req = URLRequest(url: URL(string: "https://silkdock.ai/v1/audio/transcriptions")!)req.httpMethod = "POST"req.setValue("Bearer \(ProcessInfo.processInfo.environment["SILKDOCK_API_KEY"]!)",           forHTTPHeaderField: "Authorization")req.setValue("multipart/form-data; boundary=\(boundary)", forHTTPHeaderField: "Content-Type")var body = Data()func addField(_ name: String, _ value: String) {  body.append("--\(boundary)\r\nContent-Disposition: form-data; name=\"\(name)\"\r\n\r\n\(value)\r\n".data(using: .utf8)!)}addField("model", "whisper-1")addField("language", "en")let audioData = try! Data(contentsOf: URL(fileURLWithPath: "audio.mp3"))body.append("--\(boundary)\r\nContent-Disposition: form-data; name=\"file\"; filename=\"audio.mp3\"\r\nContent-Type: audio/mpeg\r\n\r\n".data(using: .utf8)!)body.append(audioData)body.append("\r\n--\(boundary)--\r\n".data(using: .utf8)!)req.httpBody = bodylet (data, _) = try! await URLSession.shared.data(for: req)print(String(data: data, encoding: .utf8)!)
using OpenAI;using OpenAI.Audio;var client = new AudioClient(  model: "whisper-1",  credential: new System.ClientModel.ApiKeyCredential(      Environment.GetEnvironmentVariable("SILKDOCK_API_KEY")!),  options: new OpenAIClientOptions {      Endpoint = new Uri("https://silkdock.ai/v1")  });var result = await client.TranscribeAudioAsync("audio.mp3");Console.WriteLine(result.Value.Text);
using System.Net.Http;var client = new HttpClient();client.DefaultRequestHeaders.Add("Authorization",  $"Bearer {Environment.GetEnvironmentVariable("SILKDOCK_API_KEY")}");using var form = new MultipartFormDataContent();form.Add(new StringContent("whisper-1"), "model");form.Add(new StringContent("en"), "language");form.Add(new ByteArrayContent(await File.ReadAllBytesAsync("audio.mp3")), "file", "audio.mp3");var res = await client.PostAsync("https://silkdock.ai/v1/audio/transcriptions", form);Console.WriteLine(await res.Content.ReadAsStringAsync());
require "openai"client = OpenAI::Client.new(access_token: ENV["SILKDOCK_API_KEY"],uri_base: "https://silkdock.ai/v1")response = client.audio.transcribe(parameters: {  model: "whisper-1",  file:  File.open("audio.mp3", "rb")})puts response["text"]
require "net/http"uri = URI("https://silkdock.ai/v1/audio/transcriptions")req = Net::HTTP::Post.new(uri)req["Authorization"] = "Bearer #{ENV['SILKDOCK_API_KEY']}"form = Net::HTTP::Post::Multipart.new(uri.path,"model"    => "whisper-1","language" => "en","file"     => UploadIO.new("audio.mp3", "audio/mpeg"))form["Authorization"] = req["Authorization"]res = Net::HTTP.start(uri.host, uri.port, use_ssl: true) { |h| h.request(form) }puts JSON.parse(res.body)["text"]
import com.openai.client.OpenAIClientimport com.openai.client.okhttp.OpenAIOkHttpClientimport com.openai.models.*import java.nio.file.Pathval client: OpenAIClient = OpenAIOkHttpClient.builder()  .apiKey(System.getenv("SILKDOCK_API_KEY"))  .baseURL("https://silkdock.ai/v1")  .build()val transcription = client.audio().transcriptions().create(  TranscriptionCreateParams.builder()      .model(AudioModel.WHISPER_1)      .file(Path.of("audio.mp3"))      .build())println(transcription.text())
import java.net.http.*import java.net.URIimport java.nio.file.*import java.util.UUIDval boundary = UUID.randomUUID().toString()val fileBytes = Files.readAllBytes(Path.of("audio.mp3"))val body = buildString {  append("--$boundary
")  append("Content-Disposition: form-data; name="model"

whisper-1
")  append("--$boundary
")  append("Content-Disposition: form-data; name="language"

en
")  append("--$boundary
")  append("Content-Disposition: form-data; name="file"; filename="audio.mp3"
")  append("Content-Type: audio/mpeg

")}.toByteArray() + fileBytes + "
--$boundary--
".toByteArray()val req = HttpRequest.newBuilder()  .uri(URI.create("https://silkdock.ai/v1/audio/transcriptions"))  .header("Authorization", "Bearer ${System.getenv("SILKDOCK_API_KEY")}")  .header("Content-Type", "multipart/form-data; boundary=$boundary")  .POST(HttpRequest.BodyPublishers.ofByteArray(body))  .build()println(HttpClient.newHttpClient().send(req, HttpResponse.BodyHandlers.ofString()).body())
use reqwest::blocking::{Client, multipart};fn main() -> Result<(), Box<dyn std::error::Error>> {  let form = multipart::Form::new()      .text("model", "whisper-1")      .text("language", "en")      .file("file", "audio.mp3")?;  let res = Client::new()      .post("https://silkdock.ai/v1/audio/transcriptions")      .header("Authorization", format!("Bearer {}", std::env::var("SILKDOCK_API_KEY")?))      .multipart(form)      .send()?;  println!("{}", res.text()?);  Ok(())}
POST /v1/audio/transcriptions HTTP/1.1Host: silkdock.aiAuthorization: Bearer <YOUR_API_KEY>Content-Type: multipart/form-data; boundary=----boundary------boundaryContent-Disposition: form-data; name="model"whisper-1------boundaryContent-Disposition: form-data; name="language"en------boundaryContent-Disposition: form-data; name="file"; filename="audio.mp3"Content-Type: audio/mpeg<binary audio data>------boundary--
import 'dart:io';import 'package:http/http.dart' as http;void main() async {final req = http.MultipartRequest(  'POST',  Uri.parse('https://silkdock.ai/v1/audio/transcriptions'),)  ..headers['Authorization'] = 'Bearer ${const String.fromEnvironment("SILKDOCK_API_KEY")}'  ..fields['model'] = 'whisper-1'  ..fields['language'] = 'en'  ..files.add(await http.MultipartFile.fromPath('file', 'audio.mp3'));final res = await req.send();print(await res.stream.bytesToString());}
library(httr2)req <- request("https://silkdock.ai/v1/audio/transcriptions") |>req_headers(Authorization = paste("Bearer", Sys.getenv("SILKDOCK_API_KEY"))) |>req_body_multipart(  model    = "whisper-1",  language = "en",  file     = curl::form_file("audio.mp3", type = "audio/mpeg"))resp <- req_perform(req)cat(resp_body_json(resp)$text)
(* requires cohttp-lwt-unix and multipart_form *)(* Simple approach using curl via shell *)let () =let key = Sys.getenv "SILKDOCK_API_KEY" inlet cmd = Printf.sprintf  {|curl -s -X POST https://silkdock.ai/v1/audio/transcriptions     -H "Authorization: Bearer %s"     -F "model=whisper-1"     -F "language=en"     -F "[email protected]"|}  keyinprint_string (Unix.open_process_in cmd |> (fun ch ->  let buf = Buffer.create 256 in  (try while true do Buffer.add_channel buf ch 1 done   with End_of_file -> ());  Buffer.contents buf))

Response

{
  "text": "你好，欢迎使用语音识别服务。"
}

For response_format: "verbose_json":

{
  "task": "transcribe",
  "language": "english",
  "duration": 3.14,
  "text": "你好，欢迎使用语音识别服务。",
  "segments": [
    {
      "id": 0,
      "start": 0.0,
      "end": 3.14,
      "text": "你好，欢迎使用语音识别服务。",
      "tokens": [50364, 2425, 11, 3250, 281, 264, 2348, 12, 1353, 12, 6123, 2643, 13, 50521]
    }
  ]
}

Last updated on

Text-to-Speech

Convert text to speech audio.

Video Generation

Generate videos from a text prompt or reference image.

On this page

Parameters
Examples
Response