Skip to main content

PlayAI

Mastra 中的 PlayAI 语音实现通过 PlayAI 的 API 提供文本转语音功能。

🌐 The PlayAI voice implementation in Mastra provides text-to-speech capabilities using PlayAI's API.

使用示例
Direct link to 使用示例

🌐 Usage Example

import { PlayAIVoice } from "@mastra/voice-playai";

// Initialize with default configuration (uses PLAYAI_API_KEY environment variable and PLAYAI_USER_ID environment variable)
const voice = new PlayAIVoice();

// Initialize with default configuration
const voice = new PlayAIVoice({
  speechModel: {
    name: "PlayDialog",
    apiKey: process.env.PLAYAI_API_KEY,
    userId: process.env.PLAYAI_USER_ID,
  },
  speaker: "Angelo", // Default voice
});

// Convert text to speech with a specific voice
const audioStream = await voice.speak("Hello, world!", {
  speaker:
    "s3://voice-cloning-zero-shot/b27bc13e-996f-4841-b584-4d35801aea98/original/manifest.json", // Dexter voice
});

构造函数参数
Direct link to 构造函数参数

🌐 Constructor Parameters

speechModel?:

PlayAIConfig
= { name: 'PlayDialog' }
Configuration for text-to-speech functionality

speaker?:

string
= First available voice ID
Default voice ID to use for speech synthesis

PlayAI配置
Direct link to PlayAI配置

🌐 PlayAIConfig

name?:

'PlayDialog' | 'Play3.0-mini'
= 'PlayDialog'
The PlayAI model to use

apiKey?:

string
PlayAI API key. Falls back to PLAYAI_API_KEY environment variable

userId?:

string
PlayAI user ID. Falls back to PLAYAI_USER_ID environment variable

方法
Direct link to 方法

🌐 Methods

speak()
Direct link to speak()

使用配置的语音模型和声音将文本转换为语音。

🌐 Converts text to speech using the configured speech model and voice.

input:

string | NodeJS.ReadableStream
Text to convert to speech. If a stream is provided, it will be converted to text first.

options.speaker?:

string
= Constructor's speaker value
Override the default speaker for this request

返回：Promise<NodeJS.ReadableStream>。

🌐 Returns: Promise<NodeJS.ReadableStream>.

getSpeakers()
Direct link to getSpeakers()

返回一个可用语音选项的数组，每个节点包含：

🌐 Returns an array of available voice options, where each node contains:

name:

string
Name of the voice

accent:

string
Accent of the voice (e.g., 'US', 'British', 'Australian')

gender:

'M' | 'F'
Gender of the voice

age:

'Young' | 'Middle' | 'Old'
Age category of the voice

style:

'Conversational' | 'Narrative'
Speaking style of the voice

voiceId:

string
Unique identifier for the voice

listen()
Direct link to listen()

此方法不被 PlayAI 支持，会导致错误。PlayAI 不提供语音转文本功能。

🌐 This method is not supported by PlayAI and will throw an error. PlayAI does not provide speech-to-text functionality.

注意
Direct link to 注意

🌐 Notes

  • PlayAI需要API密钥和用户ID进行身份验证
  • 该服务提供两种模型：'PlayDialog' 和 'Play3.0-mini'
  • 每个语音都有一个独特的 S3 清单 ID，调用 API 时必须使用该 ID
目录