Documentation

AudioTTS implements Pipeline

Implements an OpenAI TTS pipeline for audio generation.

This pipeline uses an underlying driver (default: GuzzleDriver) to communicate with the OpenAI API for text-to-speech generation. It sets the model and API endpoint based on configuration, applies required HTTP headers including the access token, and expects an IVFSprompt instance to configure the request. The resulting audio output is stored as a file (with a UUID-based filename).

You can find available voices at: https://platform.openai.com/docs/guides/text-to-speech They include: alloy, ash, coral, echo, fable, onyx, nova, sage, shimmer

Table of Contents

Interfaces

Pipeline
Defines the required methods for Ai Model Pipelines, which are required for compatibility with LaravelNeuro Agent Networking features.

Properties

$accessToken  : mixed
The OpenAI access token retrieved from configuration.
$driver  : GuzzleDriver
The driver instance used for HTTP requests.
$fileType  : string
The output file type (e.g., "mp3").
$model  : mixed
The model identifier used for the API request.
$prompt  : mixed
The prompt input, extracted from an IVFSprompt instance.

Methods

__construct()  : mixed
AudioTTS constructor.
driver()  : Driver
Accesses the injected Driver instance.
driverClass()  : string
Retrieves the class name of the default associated driver.
getDriver()  : Driver
Retrieves the current driver.
getModel()  : mixed
Retrieves the current model identifier.
getPrompt()  : mixed
Retrieves the current prompt input.
output()  : mixed
Executes the API request and returns the stored output.
promptClass()  : string
Retrieves the class name of the default associated prompt.
raw()  : mixed
Retrieves the raw API response.
setModel()  : self
Sets the model for the pipeline.
setPrompt()  : self
Sets the prompt for the pipeline.
store()  : mixed
Executes the API request, stores the audio output as a file, and returns file metadata.
stream()  : Generator
Executes a streaming API request.

Properties

$accessToken

The OpenAI access token retrieved from configuration.

protected mixed $accessToken

$fileType

The output file type (e.g., "mp3").

protected string $fileType

$model

The model identifier used for the API request.

protected mixed $model

$prompt

The prompt input, extracted from an IVFSprompt instance.

protected mixed $prompt

Methods

__construct()

AudioTTS constructor.

public __construct([Driver $driver = new GuzzleDriver() ]) : mixed

Retrieves configuration values for the API endpoint, model, and access token, sets up the underlying driver, and configures necessary HTTP headers. Throws an exception if any required configuration value is missing.

Parameters
$driver : Driver = new GuzzleDriver()

An instance implementing the Driver contract.

Tags
throws
InvalidArgumentException

if required configuration values are missing.

driver()

Accesses the injected Driver instance.

public driver() : Driver
Return values
Driver —

the Driver instance stored in this instance of the class.

driverClass()

Retrieves the class name of the default associated driver.

public driverClass() : string
Return values
string

getDriver()

Retrieves the current driver.

public getDriver() : Driver
Return values
Driver —

The driver instance.

getModel()

Retrieves the current model identifier.

public getModel() : mixed
Return values
mixed —

The model identifier.

getPrompt()

Retrieves the current prompt input.

public getPrompt() : mixed
Return values
mixed —

The prompt input.

output()

Executes the API request and returns the stored output.

public output([bool $json = true ]) : mixed

This method is an alias for the store() method.

Parameters
$json : bool = true

Optional. If true, returns JSON-encoded file metadata.

Return values
mixed —

The file metadata or its JSON-encoded representation.

promptClass()

Retrieves the class name of the default associated prompt.

public promptClass() : string
Return values
string

raw()

Retrieves the raw API response.

public raw() : mixed
Return values
mixed —

The raw audio data.

setModel()

Sets the model for the pipeline.

public setModel(mixed $model) : self

Updates both the pipeline property and the driver's request payload.

Parameters
$model : mixed

The model identifier.

Return values
self

setPrompt()

Sets the prompt for the pipeline.

public setPrompt(IVFSprompt $prompt) : self

Expects an IVFSprompt instance. Extracts input, voice, and format from the prompt, configures the driver's prompt, and updates the request with the appropriate voice and response_format parameters. Also stores the file type based on the prompt format.

Parameters
$prompt : IVFSprompt

An IVFSprompt instance.

Tags
throws
InvalidArgumentException

If the provided prompt is not an IVFSprompt.

Return values
self

store()

Executes the API request, stores the audio output as a file, and returns file metadata.

public store([bool $json = false ]) : mixed

Generates a UUID-based filename with the defined file type, saves the audio data using the driver's fileMake method, and returns metadata about the stored file.

Parameters
$json : bool = false

Optional. If true, returns JSON-encoded file metadata.

Return values
mixed —

The file metadata array or its JSON-encoded representation.

stream()

Executes a streaming API request.

public stream() : Generator

This pipeline does not support streaming mode.

Tags
throws
Exception

Always throws an exception indicating streaming is not supported.

Return values
Generator 

        

        
    




    

    

                                

                

                                
    

        On this page

        
    


                

                            

            

    

        

            
Search results