Murf

Mastra 中的 Murf 语音实现提供了使用 Murf AI 语音服务的文本转语音（TTS）功能。它支持多种语言的多种语音。

🌐 The Murf voice implementation in Mastra provides text-to-speech (TTS) capabilities using Murf's AI voice service. It supports multiple voices across different languages.

使用示例

🌐 Usage Example

import { MurfVoice } from "@mastra/voice-murf";

// Initialize with default configuration (uses MURF_API_KEY environment variable)
const voice = new MurfVoice();

// Initialize with custom configuration
const voice = new MurfVoice({
  speechModel: {
    name: "GEN2",
    apiKey: "your-api-key",
    properties: {
      format: "MP3",
      rate: 1.0,
      pitch: 1.0,
      sampleRate: 48000,
      channelType: "STEREO",
    },
  },
  speaker: "en-US-cooper",
});

// Text-to-Speech with default settings
const audioStream = await voice.speak("Hello, world!");

// Text-to-Speech with custom properties
const audioStream = await voice.speak("Hello, world!", {
  speaker: "en-UK-hazel",
  properties: {
    format: "WAV",
    rate: 1.2,
    style: "casual",
  },
});

// Get available voices
const voices = await voice.getSpeakers();

构造函数参数

🌐 Constructor Parameters

speechModel?:

MurfConfig

= { name: 'GEN2' }

Configuration for text-to-speech functionality

speaker?:

string

= 'en-UK-hazel'

Default voice ID to use for text-to-speech

MurfConfig

name:

'GEN1' | 'GEN2'

= 'GEN2'

The Murf model generation to use

apiKey?:

string

Murf API key. Falls back to MURF_API_KEY environment variable

properties?:

object

Default properties for all speech synthesis requests

语音属性

🌐 Speech Properties

style?:

string

Speaking style for the voice

rate?:

number

Speech rate multiplier

pitch?:

number

Voice pitch adjustment

sampleRate?:

8000 | 24000 | 44100 | 48000

Audio sample rate in Hz

format?:

'MP3' | 'WAV' | 'FLAC' | 'ALAW' | 'ULAW'

Output audio format

channelType?:

'STEREO' | 'MONO'

Audio channel configuration

pronunciationDictionary?:

Record<string, string>

Custom pronunciation mappings

encodeAsBase64?:

boolean

Whether to encode the audio as base64

variation?:

number

Voice variation parameter

audioDuration?:

number

Target audio duration in seconds

multiNativeLocale?:

string

Locale for multilingual support

方法

🌐 Methods

speak()

使用 Murf 的 API 将文本转换为语音。

🌐 Converts text to speech using Murf's API.

input:

string | NodeJS.ReadableStream

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

options?:

object

Speech synthesis options

options.speaker?:

string

Override the default speaker for this request

options.properties?:

object

Override default speech properties for this request

返回：Promise<NodeJS.ReadableStream>

🌐 Returns: Promise<NodeJS.ReadableStream>

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:

voiceId:

string

Unique identifier for the voice

name:

string

Display name of the voice

language:

string

Language code for the voice

gender:

string

Gender of the voice

listen()

Murf 不支持此方法，并且会抛出错误。Murf 不提供语音转文本功能。

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

重要提示

🌐 Important Notes

1. 需要 Murf API 密钥。可以通过 MURF_API_KEY 环境变量设置，或在构造函数中传入。
2. 该服务使用 GEN2 作为默认模型版本。
3. 语音属性可以在构造函数级别设置，并可以针对每个请求进行覆盖。
4. 该服务通过格式、采样率和声道类型等属性支持广泛的音频自定义。
5. 不支持语音转文本功能。