Cloud

openai_speech

Available in: Cloud, Self-Managed

Generates audio from a text description and other attributes, using OpenAI API.

  • Common

  • Advanced

processors:
  label: ""
  openai_speech:
    server_address: https://api.openai.com/v1
    api_key: "" # No default (required)
    model: "" # No default (required)
    input: "" # No default (optional)
    voice: "" # No default (required)
processors:
  label: ""
  openai_speech:
    server_address: https://api.openai.com/v1
    api_key: "" # No default (required)
    model: "" # No default (required)
    input: "" # No default (optional)
    voice: "" # No default (required)
    response_format: "" # No default (optional)

This processor sends a text description and other attributes, such as a voice type and format to the OpenAI API, which generates audio. By default, the processor submits the entire payload of each message as a string, unless you use the input configuration field to customize it.

To learn more about turning text into spoken audio, see the OpenAI API documentation.

Fields

api_key

The API key for OpenAI API.

This field contains sensitive information that usually shouldn’t be added to a configuration directly. For more information, see Manage Secrets before adding it to your configuration.

Type: string

input

A text description of the audio you want to generate. The input field accepts a maximum of 4096 characters.

Type: string

model

The name of the OpenAI model to use.

Type: string

# Examples:
model: tts-1

# ---

model: tts-1-hd

response_format

The format to generate audio in. Default is mp3. This field supports interpolation functions.

Type: string

# Examples:
response_format: mp3

# ---

response_format: opus

# ---

response_format: aac

# ---

response_format: flac

# ---

response_format: wav

# ---

response_format: pcm

server_address

The Open API endpoint that the processor sends requests to. Update the default value to use another OpenAI compatible service.

Type: string

Default: https://api.openai.com/v1

voice

The type of voice to use when generating the audio. This field supports interpolation functions.

Type: string

# Examples:
voice: alloy

# ---

voice: echo

# ---

voice: fable

# ---

voice: onyx

# ---

voice: nova

# ---

voice: shimmer