### Setup Project Environment

Source: https://www.volcengine.com/docs/6561/2227958?lang=zh

Sets up a new project directory, extracts a code archive, activates a virtual environment, and installs project dependencies. This is required before running the code examples.

```bash
mkdir -p volcengine_get_voice_demo
tar xvzf volcengine_get_voice_demo.tar.gz -C ./volcengine_get_voice_demo
cd volcengine_get_voice_demo
python3 -m venv .venv
source .venv/bin/activate
python3 -m pip install --upgrade pip
pip3 install -e .
```

--------------------------------

### Start Session Payload Example

Source: https://www.volcengine.com/docs/6561/1739229?lang=zh

Example JSON payload for starting a session, including speaker and audio generation parameters like emotion and loudness.

```JSON
{"user":{"uid":"YOURUID"},"req_params":{"speaker":"zh_female_roumeinvyou_emo_v2_mars_bigtts","audio_params":{"emotion":"excited","loudness_rate":50}}}
```

--------------------------------

### Run Realtime Dialog API Examples

Source: https://www.volcengine.com/docs/6561/1594356?lang=zh

Commands to execute the Realtime Dialog API examples for Go and Python after installation. The Go command includes a verbosity flag.

```Shell
go run . -v=0
```

```Shell
python main.py
```

--------------------------------

### Main Method for Volcengine API Interaction Setup in Java

Source: https://www.volcengine.com/docs/6561/1476626?lang=zh

This is the main entry point for the example, setting up initial parameters like Access Key ID, Secret Access Key, endpoint, and service details for signing API requests.

```java
    public static void main(String[] args) throws Exception {
        String AccessKeyID = "";
        String SecretAccessKey = "";

        String endpoint = "open.volcengineapi.com";
        String path = "/";
        String service = "speech_saas_prod";
        String region = "cn-north-1";
        String schema = "https";
        Sign sign = new Sign(region, service, schema, endpoint, path, AccessKeyID, SecretAccessKey);

    }
```

--------------------------------

### Setup Project Environment

Source: https://www.volcengine.com/docs/6561/2227958?lang=zh

This sequence of commands sets up a new project environment, installs dependencies, and activates a virtual environment. It's recommended for managing project-specific packages.

```bash
mkdir -p volcengine_upgrade_voice_demo
tar xvzf volcengine_upgrade_voice_demo.tar.gz -C ./volcengine_upgrade_voice_demo
cd volcengine_upgrade_voice_demo
python3 -m venv .venv
source .venv/bin/activate
python3 -m pip install --upgrade pip
pip3 install -e .
```

--------------------------------

### Setup Voice Cloning Demo Environment

Source: https://www.volcengine.com/docs/6561/2227958?lang=zh

These commands set up the voice cloning demo environment by creating a directory, extracting the code package, creating a virtual environment, activating it, and installing project dependencies.

```bash
mkdir -p volcengine_voice_clone_demo
tar xvzf volcengine_voice_clone_demo.tar.gz -C ./volcengine_voice_clone_demo
cd volcengine_voice_clone_demo
python3 -m venv .venv
source .venv/bin/activate
python3 -m pip install --upgrade pip
pip3 install -e .

```

--------------------------------

### Install Python Dependencies

Source: https://www.volcengine.com/docs/6561/1329505?lang=zh

Installs and upgrades pip, then installs the project dependencies in a virtual environment. This is a prerequisite for running Python examples.

```bash
python3 -m pip install --upgrade pip
```

```bash
mkdir -p volcengine_bidirection_demo
tar xvzf volcengine_bidirection_demo.tar.gz -C ./volcengine_bidirection_demo
cd volcengine_bidirection_demo
python3 -m venv .venv
source .venv/bin/activate
python3 -m pip install --upgrade pip
pip3 install -e .
```

--------------------------------

### Install Python Dependencies

Source: https://www.volcengine.com/docs/6561/2228192?lang=zh

Installs project dependencies and sets up a virtual environment for Python. This is required before running the Python speech synthesis example.

```Bash
mkdir -p volcengine_binary_demo
tar xvzf volcengine_binary_demo.tar.gz -C ./volcengine_binary_demo
cd volcengine_binary_demo
python3 -m venv .venv
source .venv/bin/activate
python3 -m pip install --upgrade pip
pip3 install -e .
```

--------------------------------

### Receive Connection Established - SessionStarted Example

Source: https://www.volcengine.com/docs/6561/1756902?lang=zh

This is an example of the server response indicating that the connection has been successfully established.

```json
{
  "event": event.Type_SessionStarted
}
```

--------------------------------

### Install Python SDK Dependencies

Source: https://www.volcengine.com/docs/6561/1668014?lang=zh

Sets up a Python virtual environment and installs the Speech SDK and its dependencies.

```bash
mkdir -p volcengine_podcasts_demo
tar xvzf volcengine_podcasts_demo.tar.gz -C ./volcengine_podcasts_demo
cd volcengine_podcasts_demo
python3 -m venv .venv
source .venv/bin/activate
python3 -m pip install --upgrade pip
pip3 install -e .
```

--------------------------------

### Text-to-Speech Request Example

Source: https://www.volcengine.com/docs/6561/2277844?lang=zh

This JSON object demonstrates a sample request payload for the Volcengine Text-to-Speech API. It includes parameters for text prompts and image prompts, specifying voice characteristics and providing image data via base64 encoding.

```json
{
  "prompt": {
    "text_prompt": "女性，语速中等偏快，语调低沉有力",
    "image_prompt": {
      "image_bytes": 
```

--------------------------------

### Voice Design API Response Example

Source: https://www.volcengine.com/docs/6561/2277844?lang=zh

This JSON object represents a successful response from the Voice Design API, indicating available training times, creation time, language, speaker ID, demo audio URL, and training status.

```json
{
  "available_training_times": 15,
  "create_time": 1772026663000,
  "language": 0,
  "speaker_id": "S_*******",
  "demo_audio": "https://lf6-lab-speech-tt-sign.bytespeech.com/tos-cn-o-14155/o0ftE0YFM8eECAX78jC3AHopgAijApN6uMBCAi?x-expires=1773912669&x-signature=g7ui2EQVJ0PShNKC%2BArg%2Bf7ZdoQ%3D",
  "status": 2
}
```

--------------------------------

### Voice Design API Error Response Example

Source: https://www.volcengine.com/docs/6561/2277844?lang=zh

This JSON object illustrates an error response from the Voice Design API, typically returned when an operation fails. It includes an error code and a detailed error message.

```json
{
  "code": 45001001,
  "message": "请求参数有误"
}
```

--------------------------------

### 指定模型下载路径

Source: https://www.volcengine.com/docs/6561/516112?lang=zh

在调用`setup`之前指定模型下载路径。建议此路径不存放其他文件，因为模型升级时可能会清空该目录。该路径需要是一个已存在的目录。

```objectivec
/// 指定模型下载路径，这个路径建议不要放其它文件，在模型升级时可能会先清空
/// 须在 `setup` 之前调用
/// @param rootPath 模型下载路径，需要是已经存在的目录
- (void)setRootPath:(NSString*)rootPath;
```

--------------------------------

### HTTP Request Example

Source: https://www.volcengine.com/docs/6561/1756902?lang=zh

Example of an HTTP GET request to the translation API, including necessary headers.

```APIDOC
## 建连 HTTP 请求头示例 #
```
GET /api/v4/ast/v2/translate 
Host: openspeech.bytedance.com
X-Api-App-Key: 123456789
X-Api-Resource-Id: volc.service_type.10053

# 返回 Header
X-Tt-Logid: 202407261553070FACFE6D19421815D605

Plain

```
```

--------------------------------

### 设置语音SDK的引擎名称

Source: https://www.volcengine.com/docs/6561/516112?lang=zh

在调用`setup`之前设置语音SDK的引擎名称，该名称应与`SE_PARAMS_KEY_ENGINE_NAME_STRING`的配置值相同。

```objectivec
/// 设置语音SDK的引擎名称
/// 应该和 SE_PARAMS_KEY_ENGINE_NAME_STRING 的配置值相同
/// 须在 `setup` 之前调用
/// @param engineName 引擎名称
- (void)setSpeechEngineName:(NSString*)engineName;
```

--------------------------------

### Install PortAudio on macOS

Source: https://www.volcengine.com/docs/6561/1594356?lang=zh

Installs the PortAudio library on macOS using Homebrew. This is a prerequisite for running the Realtime Dialog API examples.

```Bash
brew install portaudio
```

--------------------------------

### 指定是否使用线上模型

Source: https://www.volcengine.com/docs/6561/516112?lang=zh

在调用`setup`之前指定是否使用线上资源，对于无特殊需求的情况，建议设置为TRUE。

```objectivec
/// 是否使用线上资源
/// 须在 `setup` 之前调用
/// @param useOnlineModel 无特殊需求设置为 TRUE
- (void)setOnlineModelEnable:(BOOL)useOnlineModel;
```

--------------------------------

### Install PortAudio on Debian/Ubuntu

Source: https://www.volcengine.com/docs/6561/1594356?lang=zh

Installs the PortAudio development library on Debian/Ubuntu using apt-get. This is a prerequisite for running the Realtime Dialog API examples.

```Shell
sudo apt-get install portaudio19-dev
```

--------------------------------

### Run .NET Speech SDK Example

Source: https://www.volcengine.com/docs/6561/1668014?lang=zh

Execute the .NET Speech SDK example by providing your App ID, Access Token, and the text for podcast generation. Ensure you replace placeholders with your actual credentials.

```bash
dotnet run --project Volcengine/Podcasts/Volcengine.Speech.Podcasts.csproj -- --appid <appid> --access_token <access_token> --text "介绍下火山引擎"
```

--------------------------------

### 设置引擎类型

Source: https://www.volcengine.com/docs/6561/516112?lang=zh

设置语音SDK的引擎名称，应与 `SE_PARAMS_KEY_ENGINE_NAME_STRING` 的配置值相同。须在 `setup` 之前调用。

```APIDOC
## 设置引擎类型
```
/// 设置语音SDK的引擎名称
/// 应该和 SE_PARAMS_KEY_ENGINE_NAME_STRING 的配置值相同
/// 须在 `setup` 之前调用
/// @param engineName 引擎名称
- (void)setSpeechEngineName:(NSString*)engineName;

objectivec
```
```

--------------------------------

### Install PortAudio on CentOS

Source: https://www.volcengine.com/docs/6561/1594356?lang=zh

Installs the PortAudio library and development files on CentOS using yum. This is a prerequisite for running the Realtime Dialog API examples.

```Bash
sudo yum install -y portaudio portaudio-devel
```

--------------------------------

### Run Node.js Speech SDK Example

Source: https://www.volcengine.com/docs/6561/1668014?lang=zh

Execute the Node.js Speech SDK example using ts-node. Provide your App ID, Access Token, and the text for podcast generation. Replace placeholders with your actual credentials.

```bash
npx ts-node src/volcengine/podcasts.ts --appid <appid> --access_token <access_token> --text "介绍下火山引擎"
```

--------------------------------

### Translated Text Start - TranslationSubtitleStart Example

Source: https://www.volcengine.com/docs/6561/1756902?lang=zh

Marks the beginning of the translated text transmission. Includes the start timestamp and a speaker change signal if related features are enabled.

```json
{
  "event": event.Type_TranslationSubtitleStart,
  "start_time": xxx,
  "spk_chg": false    //默认为false，如果检测到此句说话人发生切换，那么为true
}
```

--------------------------------

### 指定是否使用线上模型

Source: https://www.volcengine.com/docs/6561/516112?lang=zh

指定是否使用线上资源。无特殊需求时设置为 TRUE。须在 `setup` 之前调用。

```APIDOC
## 指定是否使用线上模型
```
/// 是否使用线上资源
/// 须在 `setup` 之前调用
/// @param useOnlineModel 无特殊需求设置为 TRUE
- (void)setOnlineModelEnable:(BOOL)useOnlineModel;

objectivec
```
```

--------------------------------

### Original Text Start - SourceSubtitleStart Example

Source: https://www.volcengine.com/docs/6561/1756902?lang=zh

Marks the beginning of the original text transmission. Includes the start timestamp and a speaker change signal if related features are enabled.

```json
{
  "event": event.Type_SourceSubtitleStart,
  "start_time": xxx,
  "spk_chg": false    //默认为false，如果检测到此句说话人发生切换，那么为true
}
```

--------------------------------

### Query Speech API Task Result Example

Source: https://www.volcengine.com/docs/6561/80909?lang=zh

Example of an HTTP GET request to query the status or result of a speech processing task using the task ID.

```http
GET /api/v1/vc/query?appid=lv&id=fc5aa03e-6ae4-46a3-b8cf-1910a44e0d8a HTTP/1.1
Host: openspeech.bytedance.com
```

--------------------------------

### Example Text Response with Timestamps

Source: https://www.volcengine.com/docs/6561/1598757?lang=zh

An example of a text response containing synthesized text and detailed word-level timing information, including start time, end time, and confidence scores.

```json
{
    "code": 0,
    "message": "",
    "data": null,
    "sentence": {
        "text": "其他人。",
        "words": [
            {
                "confidence": 0.8531248,
                "endTime": 0.315,
                "startTime": 0.205,
                "word": "其"
            },
            {
                "confidence": 0.9710379,
                "endTime": 0.515,
                "startTime": 0.315,
                "word": "他"
            },
            {
                "confidence": 0.9189944,
                "endTime": 0.815,
                "startTime": 0.515,
                "word": "人。"
            }
        ]
    }
}
```

--------------------------------

### Query Synthesis Result Request Example

Source: https://www.volcengine.com/docs/6561/1096680?lang=zh

This is an example of a GET request to query the status of a text-to-speech synthesis task. Ensure you replace placeholder values with your actual AppID and Task ID.

```http
https://openspeech.bytedance.com/api/v1/tts_async/query?appid=123456&task_id=bd0c2171-4b38-4c05-b685-11f3d240ee8d
```

--------------------------------

### Set TTS Voice Type

Source: https://www.volcengine.com/docs/6561/516112?lang=zh

Specify the TTS voice type(s) to be used. Examples include 'BV001_streaming' and 'BV002_streaming'. Must be called before `setup`.

```objectivec
/// 设置想要使用的 TTS 音色
/// 须在 `setup` 之前调用
/// @param voiceTypes 如 @[@"BV001_streaming", @"BV002_streaming"]
- (void)setTtsVoiceType:(NSArray*)voiceType;
```

--------------------------------

### Demonstrate API Request Signing in Java

Source: https://www.volcengine.com/docs/6561/1476625?lang=zh

Main method to set up API credentials, endpoint, and parameters, then initiate a signed GET request using the Sign class.

```Java
public static void main(String[] args) throws Exception {
        String AccessKeyID = "";
        String SecretAccessKey = "";

        String endpoint = "open.volcengineapi.com";
        String path = "/";
        String service = "speech_saas_prod";
        String region = "cn-north-1";
        String schema = "https";
        Sign sign = new Sign(region, service, schema, endpoint, path, AccessKeyID, SecretAccessKey);

        String version = "2021-08-30";
        Date date = new Date();
        String action = "UsageMonitoring";
        Map<String, String> queryParams = Map.of(
                "AppID", "APPID真实值",
                "ResourceID", "ResourceID真实值",
                "Start", "2025-02-23",
                "End", "2025-02-25",
                "Mode", "daily"
        );
        sign.doRequest("GET", queryParams, null, date, action, version);
    }
}
```

--------------------------------

### List API Keys Request Example

Source: https://www.volcengine.com/docs/6561/1801323?lang=zh

This example demonstrates how to make a POST request to list API keys. Ensure the Host, Content-Type, X-Date, X-Content-Sha256, and Authorization headers are correctly set.

```text
POST /?Action=ListAPIKeys&Version=2025-05-20 HTTP/1.1
Host: https://open.volcengineapi.com
Content-Type: application/json; charset=UTF-8
X-Date: 20250819T031544Z
X-Content-Sha256: 287e874e******d653b44d21e
Authorization: HMAC-SHA256 Credential=Adfks******wekfwe/20250819/cn-beijing/speech_saas_prod/request, SignedHeaders=host;x-content-sha256;x-date, Signature=47a7d934ff7b37c03938******cd7b8278a40a1057690c401e92246a0e41085f

{
"ProjectName": "default",
"OnlyAvailable": true
}
```

--------------------------------

### Original Text End - SourceSubtitleEnd Example

Source: https://www.volcengine.com/docs/6561/1756902?lang=zh

Marks the end of the original text transmission, including start time, end time, and the full text.

```json
{
  "event": event.Type_SourceSubtitleEnd,
  "start_time": xxx,
  "end_time": xxx,
  "text": "xxx"
}
```

--------------------------------

### 设置appid

Source: https://www.volcengine.com/docs/6561/516112?lang=zh

在调用`setup`之前设置从火山申请得到的appid。

```objectivec
/// 设置从火山申请得到的 appid
/// 须在 `setup` 之前调用
/// @param appId
- (void)setAppId:(NSString*)appId;
```

--------------------------------

### Go Speech Synthesis Example

Source: https://www.volcengine.com/docs/6561/1668014?lang=zh

Runs a speech synthesis command using the Volcengine Go SDK. Remember to substitute the placeholder values for App ID, Access Token, and the input text.

```bash
go run volcengine/podcasts/main.go --appid <appid> --access_token <access_token>  --text "介绍下火山引擎"
```

--------------------------------

### Android TTS Artifact ID Update

Source: https://www.volcengine.com/docs/6561/79830

Starting from version 2022.07.22, the Android TTS component uses a new Maven repository and Artifact ID. Refer to the integration guide for migration if you are using the old component.

```text
com.bytedance.speechengine:speechengine_tts_tob:1.0.48.1-bugfix
```

--------------------------------

### 指定模型存放路径

Source: https://www.volcengine.com/docs/6561/516112?lang=zh

指定模型下载路径。建议此路径不要存放其它文件，因为模型升级时可能会先清空。须在 `setup` 之前调用。

```APIDOC
## 指定模型存放路径
```
/// 指定模型下载路径，这个路径建议不要放其它文件，在模型升级时可能会先清空
/// 须在 `setup` 之前调用
/// @param rootPath 模型下载路径，需要是已经存在的目录
- (void)setRootPath:(NSString*)rootPath;

objectivec
```
```

--------------------------------

### Query Speech API Task Result

Source: https://www.volcengine.com/docs/6561/149749?lang=zh

Example of an HTTP GET request to query the status or result of a speech processing task. Ensure you replace 'your_appid' with your actual application ID and use the 'id' returned from the submit interface.

```http
GET /api/v1/vc/ata/query?appid=your_appid&id=fc5aa03e-6ae4-46a3-b8cf-1910a44e0d8a HTTP/1.1
Host: openspeech.bytedance.com
```

--------------------------------

### Go Speech Synthesis Example

Source: https://www.volcengine.com/docs/6561/2228192?lang=zh

Runs the Go program for speech synthesis. Pass your App ID, Access Token, voice type, and the text content as arguments.

```Bash
go run volcengine/binary/main.go --appid <appid> --access_token <access_token> --voice_type <voice_type> --text "**你好**，我是火山引擎的语音合成服务。"
```

--------------------------------

### Start Engine

Source: https://www.volcengine.com/docs/6561/1739228?lang=zh

Starts the engine by sending the StartSession command. It's recommended to call a synchronous stop first to avoid issues with SDK's internal asynchronous threads. The `startSessionPayload` parameter contains audio generation parameters.

```objectivec
// Note: Call synchronous stop first to avoid issues with SDK's internal asynchronous threads
[self.engine sendDirective:SEDirectiveSyncStopEngine];
// Start BiTTS engine
SEEngineErrorCode ret = [self.engine sendDirective:SEDirectiveStartEngine data: startSessionPayload];
if (ret != SENoError) {
    NSLog(@"Send directive say hello failed: %d", ret);
    return;
}

```

```objectivec
"{\"user\":{\"uid\":\"YOURUID\"},\"req_params\":{\"speaker\":\"zh_female_roumeinvyou_emo_v2_mars_bigtts\",\"audio_params\":{\"emotion\":\"excited\",\"loudness_rate\":50}}}"
```

--------------------------------

### Install Python Pip

Source: https://www.volcengine.com/docs/6561/1668014?lang=zh

Installs or upgrades the pip package installer for Python.

```bash
python3 -m pip install --upgrade pip
```