Tasks

Text To Speech

Converts text input into spoken audio using AI voice models. Useful for dynamic voice generation, automated responses, and media creation.

# Basic Usage

Task to generate an audio file from text input.

# Parameters

# input

required

string

The text that will be converted into speech.

# voice

optional

string

The voice model to use for the generated audio. Options are alloy, echo, fable, onyx, nova, and shimmer.

# model

optional

string

The specific text-to-speech model version to use. Options are tts-1 or tts-1-hd.

# filename

optional

string

The name of the file saved on Stubber. Do not include a file extension; the system appends this automatically based on the response format.

# response_format

optional

string

The audio file format to generate. Options are mp3, opus, aac, flac, wav, and pcm.

# speed

optional

number

The playback speed of the generated speech. The value must be between 0.25 and 4.0.

Default: 1.0

# disable_model_response

optional

boolean

If set to true, the model will not automatically post the generated audio in a feedback action. The file will still be generated and available within the task response payload.

# Result

# Properties

# request

The configuration parameters applied during the audio generation process, echoing back the supplied variables.

# speech

The generated file's metadata object. This includes essential file routing information such as the filename, fileuuid, and contentType, which can be referenced by subsequent tasks (like attach_file).